{ "version": "2.6.3", "generated_at": "2026-08-19T07:06:58+00:00", "mode": "provider_specific_source_expansion_parsers", "summary": { "candidates_seen": 1379, "candidates_after_provider_parsers": 1384, "supported_candidates": 519, "provider_specific_updated": 524, "changed_candidates": 519, "paired_candidates": 5, "promotion_ready": 278, "blocked_runtime_or_hosting": 2, "status_counts": { "token_candidate_ready": 273, "insufficient_token_component": 244, "runtime_or_hosting_not_promoted": 2, "provider_not_supported": 860, "paired_component_candidate_ready": 5 }, "supported_providers": 33, "definition_de": "Anbieterspezifische Zusatzparser normalisieren zusätzliche Quellen nach Modellnamen, Tokenkomponente und Route. Sie erhöhen die Abdeckung, markieren aber weiterhin Prüfbedarf für Region, Vertrag und Modellalias.", "definition_en": "Provider-specific expansion parsers normalize additional sources by model name, token component and route. They improve coverage while keeping region, contract path and model alias under review.", "version": "2.6.3", "generated_at": "2026-08-19T07:06:58+00:00" }, "provider_summary": [ { "provider": "DeepInfra", "candidate_count": 340, "provider_specific_candidates": 340, "promotion_ready": 244, "paired_candidates": 0, "example_models": [ "google/gemma-2-9b-it", "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "stepfun-ai/Step-3.5-Flash", "Qwen/Qwen3-Reranker-4B", "google/gemma-3-27b-it", "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "google/veo-3.1-fast", "Qwen/Qwen3-Embedding-8B-batch" ] }, { "provider": "Together AI", "candidate_count": 43, "provider_specific_candidates": 43, "promotion_ready": 33, "paired_candidates": 5, "example_models": [ "Kimi K3", "Qwen", "Qwen", "Qwen", "Qwen", "Qwen", "Kimi K3", "Kimi K3" ] }, { "provider": "Fireworks AI", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 1, "paired_candidates": 0, "example_models": [ "Qwen3 8B", "Qwen3 8B" ] }, { "provider": "azure", "candidate_count": 149, "provider_specific_candidates": 149, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure/command-r-plus", "azure/eu/gpt-4o-2024-08-06", "azure/eu/gpt-4o-2024-11-20", "azure/eu/gpt-4o-mini-2024-07-18", "azure/eu/gpt-4o-mini-realtime-preview-2024-12-17", "azure/eu/gpt-4o-realtime-preview-2024-10-01", "azure/eu/gpt-4o-realtime-preview-2024-12-17", "azure/eu/gpt-5-2025-08-07" ] }, { "provider": "bedrock", "candidate_count": 145, "provider_specific_candidates": 145, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "ai21.jamba-1-5-large-v1:0", "ai21.jamba-1-5-mini-v1:0", "ai21.jamba-instruct-v1:0", "amazon.nova-2-multimodal-embeddings-v1:0", "anthropic.claude-3-5-haiku-20241022-v1:0", "anthropic.claude-3-5-sonnet-20240620-v1:0", "anthropic.claude-3-5-sonnet-20241022-v2:0", "anthropic.claude-3-7-sonnet-20240620-v1:0" ] }, { "provider": "openai", "candidate_count": 114, "provider_specific_candidates": 114, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "chatgpt-4o-latest", "gpt-4o-transcribe-diarize", "ft:gpt-3.5-turbo", "ft:gpt-3.5-turbo-0125", "ft:gpt-3.5-turbo-0613", "ft:gpt-3.5-turbo-1106", "ft:gpt-4-0613", "ft:gpt-4o-2024-08-06" ] }, { "provider": "azure_ai", "candidate_count": 91, "provider_specific_candidates": 91, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure_ai/claude-haiku-4-5", "azure_ai/claude-opus-4-5", "azure_ai/claude-opus-4-6", "azure_ai/claude-opus-4-7", "azure_ai/claude-fable-5", "azure_ai/claude-opus-5", "azure_ai/claude-opus-4-8", "azure_ai/claude-opus-4-1" ] }, { "provider": "bedrock_converse", "candidate_count": 82, "provider_specific_candidates": 82, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "amazon.nova-lite-v1:0", "amazon.nova-2-lite-v1:0", "amazon.nova-2-pro-preview-20251202-v1:0", "apac.amazon.nova-2-lite-v1:0", "apac.amazon.nova-2-pro-preview-20251202-v1:0", "eu.amazon.nova-2-lite-v1:0", "eu.amazon.nova-2-pro-preview-20251202-v1:0", "us.amazon.nova-2-lite-v1:0" ] }, { "provider": "deepinfra", "candidate_count": 68, "provider_specific_candidates": 68, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepinfra/Gryphe/MythoMax-L2-13b", "deepinfra/NousResearch/Hermes-3-Llama-3.1-405B", "deepinfra/NousResearch/Hermes-3-Llama-3.1-70B", "deepinfra/Qwen/QwQ-32B", "deepinfra/Qwen/Qwen2.5-72B-Instruct", "deepinfra/Qwen/Qwen2.5-7B-Instruct", "deepinfra/Qwen/Qwen2.5-VL-32B-Instruct", "deepinfra/Qwen/Qwen3-14B" ] }, { "provider": "fireworks_ai", "candidate_count": 62, "provider_specific_candidates": 62, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "fireworks-ai-4.1b-to-16b", "fireworks-ai-56b-to-176b", "fireworks-ai-above-16b", "fireworks-ai-moe-up-to-56b", "fireworks-ai-up-to-4b", "fireworks_ai/accounts/fireworks/models/deepseek-coder-v2-instruct", "fireworks_ai/accounts/fireworks/models/deepseek-r1", "fireworks_ai/accounts/fireworks/models/deepseek-r1-0528" ] }, { "provider": "gemini", "candidate_count": 47, "provider_specific_candidates": 47, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini/gemini-live-2.5-flash-preview-native-audio-09-2025", "gemini/gemini-robotics-er-1.5-preview", "gemini/gemini-robotics-er-2-preview", "gemini/gemini-robotics-er-1.6-preview", "gemini/gemini-embedding-001", "gemini/gemini-embedding-2-preview", "gemini/gemini-embedding-2", "gemini/gemini-1.5-flash" ] }, { "provider": "databricks", "candidate_count": 40, "provider_specific_candidates": 40, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "databricks/databricks-claude-3-7-sonnet", "databricks/databricks-claude-haiku-4-5", "databricks/databricks-claude-opus-4", "databricks/databricks-claude-opus-4-1", "databricks/databricks-claude-opus-4-5", "databricks/databricks-claude-opus-4-6", "databricks/databricks-claude-sonnet-4", "databricks/databricks-claude-sonnet-4-1" ] }, { "provider": "vertex_ai-language-models", "candidate_count": 31, "provider_specific_candidates": 31, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini-2.0-flash", "gemini-2.0-flash-001", "gemini-2.0-flash-lite", "gemini-2.0-flash-lite-001", "gemini-2.5-flash", "gemini-2.5-flash-image", "gemini-3-pro-image", "gemini-3-pro-image-preview" ] }, { "provider": "cloudflare", "candidate_count": 30, "provider_specific_candidates": 30, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "cloudflare/@cf/meta/llama-2-7b-chat-fp16", "cloudflare/@cf/meta/llama-2-7b-chat-int8", "cloudflare/@cf/mistral/mistral-7b-instruct-v0.1", "cloudflare/@hf/thebloke/codellama-7b-instruct-awq", "cloudflare/@cf/openai/gpt-oss-120b", "cloudflare/@cf/google/gemma-2b-it-lora", "cloudflare/@cf/meta/llama-3.2-3b-instruct", "cloudflare/@cf/meta/llama-guard-3-8b" ] }, { "provider": "anthropic", "candidate_count": 24, "provider_specific_candidates": 24, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "claude-haiku-4-5-20251001", "claude-haiku-4-5", "claude-3-7-sonnet-20250219", "claude-3-haiku-20240307", "claude-3-opus-20240229", "claude-4-opus-20250514", "claude-4-sonnet-20250514", "claude-sonnet-4-5" ] }, { "provider": "dashscope", "candidate_count": 24, "provider_specific_candidates": 24, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "dashscope/deepseek-v4-flash", "dashscope/deepseek-v4-flash-0731", "dashscope/deepseek-v4-pro", "dashscope/glm-5.1", "dashscope/glm-5.2", "dashscope/kimi-k2.7-code", "dashscope/qwen-coder", "dashscope/qwen-max" ] }, { "provider": "gmi", "candidate_count": 17, "provider_specific_candidates": 17, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gmi/anthropic/claude-opus-4.5", "gmi/anthropic/claude-sonnet-4.5", "gmi/anthropic/claude-sonnet-4", "gmi/anthropic/claude-opus-4", "gmi/openai/gpt-5.2", "gmi/openai/gpt-5.1", "gmi/openai/gpt-5", "gmi/openai/gpt-4o" ] }, { "provider": "anyscale", "candidate_count": 12, "provider_specific_candidates": 12, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "anyscale/HuggingFaceH4/zephyr-7b-beta", "anyscale/codellama/CodeLlama-34b-Instruct-hf", "anyscale/codellama/CodeLlama-70b-Instruct-hf", "anyscale/google/gemma-7b-it", "anyscale/meta-llama/Llama-2-13b-chat-hf", "anyscale/meta-llama/Llama-2-70b-chat-hf", "anyscale/meta-llama/Llama-2-7b-chat-hf", "anyscale/meta-llama/Meta-Llama-3-70B-Instruct" ] }, { "provider": "baseten", "candidate_count": 11, "provider_specific_candidates": 11, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "baseten/MiniMaxAI/MiniMax-M2.5", "baseten/nvidia/Nemotron-120B-A12B", "baseten/zai-org/GLM-5", "baseten/zai-org/GLM-4.7", "baseten/zai-org/GLM-4.6", "baseten/moonshotai/Kimi-K2.5", "baseten/moonshotai/Kimi-K2-Thinking", "baseten/moonshotai/Kimi-K2-Instruct-0905" ] }, { "provider": "vertex_ai", "candidate_count": 9, "provider_specific_candidates": 9, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "vertex_ai/gemini-3-pro-preview", "vertex_ai/gemini-3-flash-preview", "vertex_ai/gemini-3.5-flash", "vertex_ai/gemini-3.6-flash", "vertex_ai/gemini-3.7-flash", "vertex_ai/gemini-3.1-pro-preview", "vertex_ai/gemini-3.1-pro-preview-customtools", "vertex_ai/gemini-embedding-2-preview" ] }, { "provider": "deepseek", "candidate_count": 8, "provider_specific_candidates": 8, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepseek-chat", "deepseek-reasoner", "deepseek/deepseek-chat", "deepseek/deepseek-coder", "deepseek/deepseek-r1", "deepseek/deepseek-reasoner", "deepseek/deepseek-v3", "deepseek/deepseek-v3.2" ] }, { "provider": "cerebras", "candidate_count": 7, "provider_specific_candidates": 7, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "cerebras/llama-3.3-70b", "cerebras/llama3.1-70b", "cerebras/llama3.1-8b", "cerebras/gpt-oss-120b", "cerebras/qwen-3-32b", "cerebras/zai-glm-4.6", "cerebras/zai-glm-4.7" ] }, { "provider": "cohere_chat", "candidate_count": 7, "provider_specific_candidates": 7, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "command-a-03-2025", "command-light", "command-r", "command-r-08-2024", "command-r-plus", "command-r-plus-08-2024", "command-r7b-12-2024" ] }, { "provider": "volcengine", "candidate_count": 3, "provider_specific_candidates": 3, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "deepseek-v3-2-251201", "glm-4-7-251222", "kimi-k2-thinking-251104" ] }, { "provider": "vertex_ai-embedding-models", "candidate_count": 3, "provider_specific_candidates": 3, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gemini-embedding-001", "gemini-embedding-2-preview", "gemini-embedding-2" ] }, { "provider": "Replicate", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "claude-3.7-sonnet The most intelligent Claude model and the first hybrid reasoning model on the market (claude-3-7-sonnet-20250219)", "deepseek-ai / deepseek-r1 A reasoning model trained with reinforcement learning" ] }, { "provider": "azure_text", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "azure/gpt-3.5-turbo-instruct-0914", "azure/gpt-35-turbo-instruct" ] }, { "provider": "nlp_cloud", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "chatdolphin", "dolphin" ] }, { "provider": "codestral", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "codestral/codestral-2405", "codestral/codestral-latest" ] }, { "provider": "cohere", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "command", "command-nightly" ] }, { "provider": "friendliai", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "friendliai/meta-llama-3.1-70b-instruct", "friendliai/meta-llama-3.1-8b-instruct" ] }, { "provider": "text-completion-openai", "candidate_count": 2, "provider_specific_candidates": 2, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gpt-3.5-turbo-instruct", "gpt-3.5-turbo-instruct-0914" ] }, { "provider": "gradient_ai", "candidate_count": 1, "provider_specific_candidates": 1, "promotion_ready": 0, "paired_candidates": 0, "example_models": [ "gradient_ai/anthropic-claude-3-opus" ] } ], "top_ready_candidates": [ { "candidate_id": "4b93b30c483ba7e12b18", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K3", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://www.together.ai/pricing", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.3, "output_usd_per_1m": 1.2, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Price per 1M tokens Model Input output MiniMax M3 $0.30 $1.20 Kimi K3 $3.00 $15.00 Qwen3.8-2.4T-A95B $2.50 $6.25 Muse Glimmer 30B $0.35 $1.50 Gemma 4 31B $0.39 $0.97 Kimi K2.7 Code $0.95 $4.00 Qwen3.7-Plus $0.32 $1.28 Ternary Bonsai 27B $0.00 $0.00 Inkling $1.00 $4.05 Inkling Small $0.50 $1.20 Kimi K2.6 $1.20 $4.50 Qwen3.5 9B $0.17 $0.25 Gemma 3n E4B Instruct $0.06 $0.12 Qwen3.6-Plus $0.50 $3.00 Displayed prices refer to the lowest resolution/duration settings.", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.3, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f972256ef4124ece9686", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 2.5, "output_usd_per_1m": 6.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.8-2.4T-A95B | Qwen/Qwen3.8-2.4T-A95B | - | $2.50 | $0.50 | $6.25 | FP4 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.5, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 6.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b7ac5d6eb7ad433ae47e", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.25, "output_usd_per_1m": 3.75, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.7 Max | Qwen/Qwen3.7-Max | - | $1.25 | - | $3.75 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.25, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.75, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "4c2be2ebcffd00dcaef8", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.5, "output_usd_per_1m": 3.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.6 Plus | Qwen/Qwen3.6-Plus | 1000000 | $0.50 | - | $3.00 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.5, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7960cbeba8524750d0ad", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.17, "output_usd_per_1m": 0.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.5 9B | Qwen/Qwen3.5-9B | 262144 | $0.17 | - | $0.25 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.17, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7acd43d91d91a0caa220", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K3", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 3.0, "output_usd_per_1m": 15.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K3 | moonshotai/Kimi-K3 | 1000000 | $3.00 | $0.30 | $15.00 | - | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 15.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3908fba4adb9d7b635d3", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K2.7 Code", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.95, "output_usd_per_1m": 4.0, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K2.7 Code | moonshotai/Kimi-K2.7-Code | 262144 | $0.95 | $0.19 | $4.00 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.95, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.0, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "95cd59ef64eab8e1ac2f", "route_provider": "Together AI", "model_provider_inferred": "Moonshot / Kimi", "model_name": "Kimi K2.6", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.2, "output_usd_per_1m": 4.5, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Moonshot | Kimi K2.6 | moonshotai/Kimi-K2.6 | 262144 | $1.20 | $0.20 | $4.50 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.2, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.5, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "52b9234650033a958a22", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "GLM-5.2", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.4, "output_usd_per_1m": 4.4, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Z.ai | GLM-5.2 | zai-org/GLM-5.2 | 512000 | $1.40 | $0.26 | $4.40 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.4, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 4.4, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5277a1dddd47a2c04a19", "route_provider": "Together AI", "model_provider_inferred": "OpenAI", "model_name": "OpenAI", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.15, "output_usd_per_1m": 0.6, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "OpenAI | GPT-OSS 120B | openai/gpt-oss-120b | 128000 | $0.15 | - | $0.60 | MXFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.15, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.6, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c46145d1e41faa9a1fa1", "route_provider": "Together AI", "model_provider_inferred": "OpenAI", "model_name": "OpenAI", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.05, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "OpenAI | GPT-OSS 20B | openai/gpt-oss-20b | 128000 | $0.05 | - | $0.20 | MXFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.05, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e39ccdb4243034e1df0d", "route_provider": "Together AI", "model_provider_inferred": "DeepSeek", "model_name": "DeepSeek", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.74, "output_usd_per_1m": 3.48, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "DeepSeek | DeepSeek-V4-Pro | deepseek-ai/DeepSeek-V4-Pro | 512000 | $1.74 | $0.20 | $3.48 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.74, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.48, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7b2f4afae0ec0ce4b186", "route_provider": "Together AI", "model_provider_inferred": "DeepSeek", "model_name": "DeepSeek", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.14, "output_usd_per_1m": 0.28, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "DeepSeek | DeepSeek-V4-Flash-0731 | deepseek-ai/DeepSeek-V4-Flash-0731 | 1000000 | $0.14 | $0.03 | $0.28 | FP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.14, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.28, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5c86fad60c7706ec2245", "route_provider": "Together AI", "model_provider_inferred": "DeepSeek", "model_name": "DeepSeek", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.32, "output_usd_per_1m": 3.96, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "DeepSeek | DeepSeek V4 Pro 0813 | deepseek-ai/DeepSeek-V4-Pro-0813 | 1048576 | $1.32 | $0.13 | $3.96 | NVFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.32, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.96, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0cfd3660e1ada089c955", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Nemotron 3 Ultra 550B A55B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.6, "output_usd_per_1m": 3.6, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "NVIDIA | Nemotron 3 Ultra 550B A55B | nvidia/nemotron-3-ultra-550b-a55b | 512300 | $0.60 | $0.20 | $3.60 | NVFP4 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.6, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 3.6, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0555467c0415bc0d5d37", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Llama 3.3 70B Instruct Turbo", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.04, "output_usd_per_1m": 1.04, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Llama 3.3 70B Instruct Turbo | meta-llama/Llama-3.3-70B-Instruct-Turbo | 131072 | $1.04 | - | $1.04 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.04, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.04, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3b4a65007c6649851f3b", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.3, "output_usd_per_1m": 0.3, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen 2.5 7B Instruct Turbo | Qwen/Qwen2.5-7B-Instruct-Turbo | 32768 | $0.30 | - | $0.30 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.3, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.3, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "594f5f070c0873e46d3b", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.39, "output_usd_per_1m": 0.97, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 4 31B Instruct | google/gemma-4-31B-it | 262144 | $0.39 | - | $0.97 | FP8 | Yes | Yes", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.39, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.97, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e8ddc65465168f1075fe", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.28, "output_usd_per_1m": 0.86, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Pearl AI | Gemma 4 31B Instruct | pearl-ai/gemma-4-31b-it | 32000 | $0.28 | - | $0.86 | INT8 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.28, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.86, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "25684b1897dcf7790aa7", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Cogito v2.1 671B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 1.25, "output_usd_per_1m": 1.25, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Deepcogito | Cogito v2.1 671B | deepcogito/cogito-v2-1-671b | 163840 | $1.25 | - | $1.25 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.25, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8ab8d00b498aaeb8a971", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.32, "output_usd_per_1m": 1.28, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Qwen | Qwen3.7 Plus | Qwen/Qwen3.7-Plus | 1000000 | $0.32 | - | $1.28 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.32, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.28, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b867c1faafa399f31c22", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 3N E4B Instruct", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.06, "output_usd_per_1m": 0.12, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 3N E4B Instruct | google/gemma-3n-E4B-it | 32768 | $0.06 | - | $0.12 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.06, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.12, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "80e77080a9f1f39d35e0", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "LFM2.5-8B-A1B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.03, "output_usd_per_1m": 0.12, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "LiquidAI | LFM2.5-8B-A1B | LiquidAI/LFM2.5-8B-A1B | 32768 | $0.03 | - | $0.12 | - | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.03, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.12, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2d21a13ef38e516f81d0", "route_provider": "Together AI", "model_provider_inferred": "Together AI", "model_name": "Muse Glimmer 30B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.35, "output_usd_per_1m": 1.5, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Muse Glimmer 30B | meta-models/Muse-Glimmer-30B | 131072 | $0.35 | $0.04 | $1.50 | FP8 | - | -", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.35, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 1.5, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e2ce6f893b6317c7a90f", "route_provider": "Together AI", "model_provider_inferred": "Google", "model_name": "Gemma 4 31B IT", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.39, "output_usd_per_1m": 0.97, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Google | Gemma 4 31B IT | google/gemma-4-31B-it | 262144 | $0.39 | $0.97", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.39, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.97, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1260d46b0472dba8be84", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Llama Guard 4 12B", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.2, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Meta | Llama Guard 4 12B | meta-llama/Llama-Guard-4-12B | 1048576 | $0.20 | $0.20", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.2, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b57fbbd07d74bdde2411", "route_provider": "Together AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen Qwen3.5 9B Qwen/Qwen3.5-9B 262144", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.17, "output_usd_per_1m": 0.25, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "Organization Model name API model string Context length Input pricing (per 1M tokens) Output pricing (per 1M tokens) Qwen Qwen3.5 9B Qwen/Qwen3.5-9B 262144 $0.17 $0.25 Google Gemma 4 31B IT google/gemma-4-31B-it 262144 $0.39 $0.97 Minimax Minimax M3 MiniMaxAI/MiniMax-M3 524288 $0.30 $1.20 Moonshot Kimi K3 moonshotai/Kimi-K3 1000000 $3.00 $15.00 Moonshot Kimi K2.7 Code moonshotai/Kimi-K2.7-Code 262144 $0.95 $4.00 Moonshot Kimi K2.6 moonshotai/Kimi-K2.6 262144 $1.20 $4.50 ​ Vision model examples L", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.17, "field": "input_usd_per_1m" }, { "component": "output_tokens", "amount_usd": 0.25, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 2, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ffb6f156b9ddbbd02684", "route_provider": "Together AI", "model_provider_inferred": "Meta / Llama", "model_name": "Meta Llama Guard 4 12B meta-llama/Llama-Guard-4-12B 1048576", "source_id": "together_pricing_page", "source_type": "official_primary", "source_url": "https://docs.together.ai/docs/serverless-models", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": 0.2, "component": "unknown", "component_usd": null, "confidence": "medium", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Together AI als zusätzlicher Inference-Anbieter mit gezieltem Parser für Serverless-Modellpreise.", "notes_en": "Together AI as additional inference provider. Candidates remain review-only until model and component are mapped.", "raw_snippet": "​ Moderation models Organization Model name API model string Context length Input pricing (per 1M tokens) Output pricing (per 1M tokens) Meta Llama Guard 4 12B meta-llama/Llama-Guard-4-12B 1048576 $0.20 $0.20 Was this page helpful?", "provider_specific_parser": "together_serverless_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 0.2, "field": "output_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Together AI", "provider_specific_note_de": "Together-AI-Kandidaten werden nach Serverless-/Token-Kontext und Modellkomponente normalisiert.", "provider_specific_note_en": "Together AI candidates are normalized by serverless/token context and model component.", "provider_specific_model_normalized": true, "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "588c0629ac203f9d7b59", "route_provider": "Fireworks AI", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen3 8B", "source_id": "fireworks_pricing_page", "source_type": "official_primary", "source_url": "https://fireworks.ai/pricing", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": 0.1, "output_usd_per_1m": null, "component": "unknown", "component_usd": null, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "Fireworks AI mit gezieltem Parser für Tokenpreis-Tabellen und Modellzeilen.", "notes_en": "Fireworks AI as additional inference provider. HTML candidates are not treated as confirmed until component mapping is clear.", "raw_snippet": "Qwen3 8B | $0.1", "provider_specific_parser": "fireworks_token_pricing", "provider_specific_parser_version": "2.6.3", "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.1, "field": "input_usd_per_1m" } ], "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "Fireworks AI", "provider_specific_note_de": "Fireworks-AI-Kandidaten werden als zusätzliche direkte Anbieterroute geführt, sofern Tokenkomponente und Preiswert plausibel sind.", "provider_specific_note_en": "Fireworks AI candidates are treated as an additional direct provider route when component and amount are plausible.", "provider_specific_model_normalized": true, "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "64a0b8d45e7227feaf50", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-2-9b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-2-9b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is a family of lightweight, state-of-the-art open models from Google. The 9B Gemma 2 model delivers class-leading performance, outperforming Llama 3 8B and other open models in its size category.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemma-2-9b-it/cover_image.e81c22c5f9e87775e9e5316c038dcd4cb8ae875e513f14e665d84ee891a73f9b.webp\", \"tags\": [\"openai\"],", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a2a69e99704b928d74cd", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B/cover_ima", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "077c2d0ad2dc6759f9b1", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "stepfun-ai/Step-3.5-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"stepfun-ai/Step-3.5-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Step 3.5 Flash is an open-source reasoning model by StepFun with 196B total parameters (11B active) using Mixture of Experts. It features a 256K context window, deep reasoning, tool calling, and agentic capabilities, achieving 97.3 on AIME 2025 and 74.4% on SWE-bench Verified.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/stepfun-ai/Step-3.5-Flash/cover_image.d2653", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2c1f1ee7713471991bc3", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Reranker-4B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Reranker-4B\", \"type\": \"reranker\", \"reported_type\": \"reranker\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B)\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Reranke", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e85f27399cba295d43bf", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-3-27b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-3-27b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3 27B is Google's latest open source model, successor to Gemma 2\", \"cover_img_url\": \"https://shared.d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5555e7ea914462380150", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 100.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron 3 Ultra is built for, frontier reasoning, orchestration, coding agents, deep research, and complex enterprise workflows. It delivers up to 5x faster inference and up to 30% lower cost for agentic workloads while supporting up to 1M token context.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/NVIDIA-Nemotron-3-Ultra-550B-A55B-BF16", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 100.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b736feaef5d817cc6e1d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "google/veo-3.1-fast", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "output_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/veo-3.1-fast\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"Veo 3.1 is the latest text-to-video model from Google that generates high-fidelity, cinematic videos with synchronized audio from a simple text prompt. It excels at creating realistic and imaginative scenes with a deep understanding of natural language and visual dynamics.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/veo-3.1-fast/cover_image.a773baaf91598677a503558b4", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "20f0677adfc5cd9f38b3", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-8B-batch", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 4.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-8B-batch\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Q", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 4.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5e74cce091f2b81c2afe", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.2-3B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.2-3B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out)\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Llama-3.2-3B-Instruct/cover_image.da2730cb3d36e267a6e76a9b1b95177e26ab22853b046c4ecbb6231f49c25ce4.webp\", \"tags\": [\"open", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2c8b33b9266c2cd7f374", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-Prover-V2-671B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-Prover-V2-671B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-Prover-V2, an open-source large language model designed for formal theorem proving in Lean 4, with initialization data collected through a recursive theorem proving pipeline powered by DeepSeek-V3. The cold-start training procedure begins by prompting DeepSeek-V3 to decompose complex problems into a series of subgoals. The proofs of resolved subgoals are s", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2e25fc92e9d7dcdc3322", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/codegemma-7b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 7.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/codegemma-7b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"CodeGemma is a collection of lightweight open code models built on top of Gemma. CodeGemma models are text-to-text and text-to-code decoder-only models and are available as a 7 billion pretrained variant that specializes in code completion and code generation tasks, a 7 billion parameter instruction-tuned variant for code chat and instruction following and a 2 billion parameter", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 7.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9e5c51c1d90b9d9e645c", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-235B-A22B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 18.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-235B-A22B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-235B-A22B/", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 18.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e22c9c3ee1b0a157d6b1", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mixtral-8x7B-Instruct-v0.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 54.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mixtral-8x7B-Instruct-v0.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mixtral is mixture of expert large language model (LLM) from Mistral AI. This is state of the art machine learning model using a mixture 8 of experts (MoE) 7b models. During inference 2 expers are selected. This architecture allows large models to be fast and cheap at inference. The Mixtral-8x7B outperforms Llama 2 70B on most benchmarks.\", \"cover_img_url\": \"https", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 54.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f6663fdbefaafb53372c", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Voxtral-Mini-3B-2507", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1666.67, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Voxtral-Mini-3B-2507\", \"type\": \"automatic-speech-recognition\", \"reported_type\": \"automatic-speech-recognition\", \"description\": \"Voxtral Mini is an enhancement of Ministral 3B, incorporating state-of-the-art audio input capabilities while retaining best-in-class text performance. It excels at speech transcription, translation and audio understanding.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Voxtral-Mini-3B-2507/cover_image.6253f2cb31c45ecaac1fbb1", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1666.67, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "653960d8487c35ebd10e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3-8B-Lunaris-v1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3-8B-Lunaris-v1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"A generalist / roleplaying model merge based on Llama 3. Sao10K has carefully selected the values based on extensive personal experimentation and has fine-tuned them to create a customized recipe.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3-8B-Lunaris-v1/cover_image.d72dfd670089af5cbe1a16a92a538bb4d50201f12892b333b63a7f91f67536e5.webp\", \"tags\": [\"openai\"]", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ca97ff69408bf5b8cada", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.8-27B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.8-27B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.8 27B is an open-weight dense vision-language model from Qwen. It is suited for coding, professional workflows, research, multimodal interaction, and long-running agent tasks, with flexible thinking that can be enabled or disabled.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3.8-27B/cover_image.c9608e87853b4db00c2879d4d9ace9e80618a1cfbddf5d8b5650b98b0427529", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "364fa8a9d80c99a0fbaa", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-Content-Safety-3.5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-Content-Safety-3.5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron Content Safety 3.5 is a multimodal safety classifier developed by NVIDIA. A compact safety model that handles text, images, and custom policies. It outputs a safe/unsafe classification plus a reasoning trace, and can be used as an inference-time guardrail, as a judge for LLM safety testing and evaluation, or with the accompanying training dataset to post-tr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e9833df946dc3791966d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3-8B-Lunaris-v1-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 4.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3-8B-Lunaris-v1-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"json\", \"openai\", \"non-reasoning\", \"structured-output\", \"flex\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 4e-06, \"cents_per_output_token\": 5e-06, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_ser", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 4.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ae13015ddeb366afc9f1", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-0.8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-0.8B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-0.8B is Alibaba's smallest model in the Qwen3.5 series, featuring a hybrid Gated Delta Networks and sparse Mixture-of-Experts architecture. Despite its compact size, it supports a 262K token context window, 201 languages, thinking/reasoning mode, and tool calling. Ideal for edge deployments, resource-constrained environments, and lightweight inference tasks.\", \"cover_img_url", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "64af68dae3eff4a8ef72", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "google/veo-3.0", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "output_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/veo-3.0\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"Veo 3 is a state-of-the-art text-to-video model from Google that generates high-fidelity, cinematic videos with synchronized audio from a simple text prompt. It excels at creating realistic and imaginative scenes with a deep understanding of natural language and visual dynamics.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/veo-3.0/cover_image.4817ee203a8eeda7540d449add885", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "6e0f6a94db9090ca3dbe", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Next-80B-A3B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Next-80B-A3B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Over the past few months, we have observed increasingly clear trends toward scaling both total parameters and context lengths in the pursuit of more powerful and agentic artificial intelligence (AI). We are excited to share our latest advancements in addressing these demands, centered on improving scaling efficiency through innovative model architecture. We call this ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ac28e842a9c7efd59a0f", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V4-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V4-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek V4 Flash is an efficiency-focused MoE model with 284B total parameters (13B active) and a 1M-token context window. It's tuned for fast inference and high-throughput use cases while still holding up on reasoning and coding tasks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V4-Flash/cover_image.816346e8186ef1652de4efda60bee06c74b36", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "253871215e25420e685c", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.2-1B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 0.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.2-1B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Meta Llama 3.2 collection of multilingual large language models (LLMs) is a collection of pretrained and instruction-tuned generative models in 1B and 3B sizes (text in/text out).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Llama-3.2-1B-Instruct/cover_image.263b22ba8551018d6792180359cadf259a4bfb41b8db163f738a304a6186d8be.webp\", \"tags\": [\"ope", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7cc13b14c7e0b283bcac", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-235B-A22B-Thinking-2507", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 23.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-235B-A22B-Thinking-2507\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-235B-A22B-Thinking-2507 is the Qwen3's new model with scaling the thinking capability of Qwen3-235B-A22B, improving both the quality and depth of reasoning. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-235B-A22B-Thinking-2507/cover_image.2b87c6645946388f890b18b46894e32d140913d73154eb6ae428e378916853c3.webp\", \"tags\": [\"openai\", \"tools\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 23.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9e39a4903af4dcc2a945", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-72B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 36.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-72B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen2.5 is a model pretrained on a large-scale dataset of up to 18 trillion tokens, offering significant improvements in knowledge, coding, mathematics, and instruction following compared to its predecessor Qwen2. The model also features enhanced capabilities in generating long texts, understanding structured data, and generating structured outputs, while supporting multilin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 36.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "30cb22b5e91a79df8a85", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-models/Muse-Glimmer-30B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 30.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-models/Muse-Glimmer-30B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Muse Glimmer is a 30B multimodal agentic model distilled from Muse Spark — reasoning, tool use, and failure recovery in a single model that runs locally on consumer hardware.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-models/Muse-Glimmer-30B/cover_image.fe61a2f36042c392ceffcf96260da98835303f0fc6336eafa6650ac86fa8d61e.webp\", \"tags\": [\"openai\", \"cc-native\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 30.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7268abd86e030cc77561", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M2.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M2.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M2.1 is a model optimized specifically for robustness in coding, tool use, instruction following, and long-horizon planning. From automating multilingual software development to executing complex, multi-step office workflows, MiniMax-M2.1 empowers developers to build the next generation of autonomous applications—all while being fully transparent, controllable, and acce", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e31e5c26b2f415806908", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "allenai/Olmo-3.1-32B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"allenai/Olmo-3.1-32B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Olmo is a series of Open language models, developed by Allen Institute for AI (Ai2), designed to enable the science of language models. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/allenai/Olmo-3.1-32B-Instruct/cover_image.4b73f75a4b04349fab603dd34590a01e1e5e4017c39e4e1a67ab4d0e4c385c4b.webp\", \"tags\": [\"openai\", \"tools\", \"json\", \"non-reasoning\", \"structured-o", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1763989d2006944a2a0a", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-OCR", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-OCR\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-OCR as an initial investigation into the feasibility of compressing long contexts via optical 2D mapping. DeepSeek-OCR consists of two components: DeepEncoder and DeepSeek3B-MoE-A570M as the decoder. Specifically, DeepEncoder serves as the core engine, designed to maintain low activations under high-resolution input while achieving high compression ratios to ensure a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c80031bb83247308bd54", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "stepfun-ai/Step-3.7-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"stepfun-ai/Step-3.7-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Step 3.7 Flash is an open-source multimodal reasoning model by StepFun with 198B total parameters (11B active) using Mixture of Experts. It accepts text and image inputs and features a 256K context window, selectable reasoning effort, tool calling, and agentic capabilities for coding and search workflows, scoring 80.9% on GPQA Diamond and 56.3% on SWE-bench Pro.\", \"cover_img", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5a6d6a20aa4af1d3b6d0", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Embed-1B-BF16", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Embed-1B-BF16\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"Nemotron-3-Embed-1B-BF16 is a compact multilingual text embedding model from NVIDIA, pruned and distilled from Ministral-3 to ~1B parameters, that maps text into 2048-dimensional dense vectors for retrieval and semantic similarity. Spanning 34 languages, it delivers state-of-the-art quality among similarly sized models for RAG and multilingual question-answering while keeping co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "adacd070a5a024e3bd68", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-70B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-70B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-70B-Instruct/cover_image.9a5d4e05f46ed0cf09ef22a6771aa701bd3ffaadfcd68fa7ca272bc8c1c7b8e6.webp\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2573cdeb4b667584bbe8", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-4-340B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 420.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-4-340B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Nemotron-4-340B-Instruct is a chat model intended for use for the English language, designed for Synthetic Data Generation\", \"cover_img_url\": \"https://shared.deepinfra.com/models/nvidia/Nemotron-4-340B-Instruct/cover_image.6223332b8dfbf8dba008d030548970e7dbee4cfb571412430cc5ff8c007b7072.webp\", \"tags\": [\"openai\", \"tools\"], \"pricing\": {\"discount\": null, \"discount_ends_at", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 420.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bf5bb5691ef358d10e5f", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-7B-Instruct-v0.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-7B-Instruct-v0.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Mistral-7B-Instruct-v0.1 Large Language Model (LLM) is a instruct fine-tuned version of the Mistral-7B-v0.1 generative text model using a variety of publicly available conversation datasets.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.1/cover_image.cdb70679749ff93eb56b8480215bb8cd1382cbeffcec00a06bdb0145be9ef511.webp\"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7a30706bcb6c88ea4c3b", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "inworld-ai/inworld-tts-1.5-mini", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"inworld-ai/inworld-tts-1.5-mini\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"Fast multilingual text-to-speech model by Inworld AI with 130+ preset voices across 15 languages. Supports voice cloning, word-level timestamps, and streaming. Optimized for low-latency applications with <130ms time-to-first-audio.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/inworld-ai/inworld-tts-1.5-mini/cover_image.4949ffe99638b5877cd72f411b5d9603d5b3b084f", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b8b4868f4ed79e0c6a79", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-8B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-E", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "eefcbb7ab8885d7019d8", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-4B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-4B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-4B is a mid-size model from Alibaba's Qwen3.5 series that delivers a strong balance of performance and efficiency. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Well-suited for complex reasoning, code generation, and agentic applications.\", \"cover_img_url\": \"https://shared.deepinfra.c", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "77adf415b64efa6b1d13", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-TTS-VoiceDesign", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2000.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-TTS-VoiceDesign\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"● Qwen3-TTS-VoiceDesign is a voice design variant of Qwen3-TTS by Alibaba's Qwen team. Instead of selecting from preset voices, you describe the voice you want in natural language — and the model generates speech in that voice. Key capabilities: - Natural language voice control — describe any", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2000.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "24365f9e6c251537d2c6", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-R1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 70.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-R1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"We introduce DeepSeek-R1, which incorporates cold-start data before RL. DeepSeek-R1 achieves performance comparable to OpenAI-o1 across math, code, and reasoning tasks. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-R1/cover_image.5d9c2c7f37588d87ed176a0663e51c26f6907914efce7045a0d6fbd4f47a8ad6.webp\", \"tags\": [\"openai\", \"tools\", \"b200\", \"json\"], ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 70.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ebe47c16fd53f10812b0", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M2.7", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M2.7\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M2.7 is MiniMax's first model deeply participating in its own evolution. M2.7 is capable of building complex agent harnesses and completing highly elaborate productivity tasks, leveraging Agent Teams, complex Skills, and dynamic tool search. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/MiniMaxAI/MiniMax-M2.7/cover_image.3804eb1bb390b9eec47841c67ba9aad2e90425", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bcd7bde344c1daee4053", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.3-70B-Instruct-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.3-70B-Instruct-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama 3.3-70B Turbo is a highly optimized version of the Llama 3.3-70B model, utilizing FP8 quantization to deliver significantly faster inference speeds with a minor trade-off in accuracy. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "026b8ca684efbe3e1e77", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-7B-Instruct-v0.3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.8, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-7B-Instruct-v0.3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mistral-7B-Instruct-v0.3 is an instruction-tuned model, next iteration of of Mistral 7B that has larger vocabulary, newer tokenizer and supports function calling.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-7B-Instruct-v0.3/cover_image.716d64cdc98717436953bde0b80dede06d7071f66cb46f1df85caaa270e5cdd6.webp\", \"tags\": [\"openai\", \"tools\"], \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.8, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "55d4fc3a5e9a834af659", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-4B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-4B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-E", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5c7378c090d51a9b2b6a", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-Nano-9B-v2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 4.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-Nano-9B-v2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA-Nemotron-Nano-9B-v2 is a large language model (LLM) trained from scratch by NVIDIA, and designed as a unified model for both reasoning and non-reasoning tasks. It responds to user queries and tasks by first generating a reasoning trace and then concluding with a final response. The model's reasoning capabilities can be controlled via a system prompt. If the us", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 4.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "841db09eb1bdd329cf90", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Embed-8B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Embed-8B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"Nemotron-3-Embed-8B is a multilingual text embedding model from NVIDIA, based on Ministral-3-8B, that maps text into 4096-dimensional dense vectors for retrieval and semantic similarity. Spanning 34 languages, it targets multilingual RAG and question-answering over large corpora and achieves state-of-the-art results on the RTEB leaderboard.\", \"cover_img_url\": \"https://shared.deepinfr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8b5873f9fb1b0b3db8bf", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "allenai/olmOCR-7B-0725-FP8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"allenai/olmOCR-7B-0725-FP8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixe", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "f8e9827726dbfa0d7da8", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.6-27B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 32.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.6-27B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3.6-27B/cover_image.92926bd9d200e5fdc4a12c0628cb5705fa45a1e1dc1c953768f53ef8f078ec6e.webp\", \"tags\": [\"input-video\", \"json\", \"multimodal\", \"reasoning\", \"tools\", \"cc-native\", \"structured-output\", \"openai\", \"priority\", \"flex\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": n", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 32.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5ff4c826fb9496f94f88", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-3-7-sonnet-latest", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 330.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-3-7-sonnet-latest\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"ocr\", \"openai\", \"tools\", \"multimodal\", \"no-free-anon\", \"json\", \"non-reasoning\", \"structured-output\", \"cc-native\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 0.00033, \"cents_per_output_token\": 0.00165, \"rate_per_input_token_cached\": 0", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 330.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a948977d5fc0c4cbb0e6", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-Guard-4-12B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 18.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-Guard-4-12B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama Guard 4 is a natively multimodal safety classifier with 12 billion parameters trained jointly on text and multiple images. Llama Guard 4 is a dense architecture pruned from the Llama 4 Scout pre-trained model and fine-tuned for content safety classification. Similar to previous versions, it can be used to classify content in both LLM inputs (prompt classification) a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 18.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "4121c43f1fa32147f0d3", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-30B-A3B-Thinking", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 29.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-30B-A3B-Thinking\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": \"h", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 29.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d261066260f13e33465a", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Max-Thinking", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 120.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Max-Thinking\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The latest flagship reasoning model in the Qwen3 family. Further enhanced by multiple innovations like adaptive tool-use and advanced test-time scaling techniques\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Max-Thinking/cover_image.fa7888e2940746f47be3fb3eaa39ecddf187d085e0b96805a24e0db063d46f59.webp\", \"tags\": [\"openai\", \"tools\", \"no-free-anon\", \"json\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 120.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2368bafd95d8cdc31cb6", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-122B-A10B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 29.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-122B-A10B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-122B-A10B is a large Mixture-of-Experts model from Alibaba's Qwen3.5 series with 122B total parameters and 10B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Excels at complex reasoning, coding, multimodal understanding, and agentic tasks with the efficiency", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 29.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7aaad57928889c53a461", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "NousResearch/Hermes-3-Llama-3.1-70B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 70.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"NousResearch/Hermes-3-Llama-3.1-70B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Hermes 3 is a generalist language model with many improvements over Hermes 2, including advanced agentic capabilities, much better roleplaying, reasoning, multi-turn conversation, long context coherence, and improvements across the board.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/NousResearch/Hermes-3-Llama-3.1-70B/cover_image.99114748d1a7e2336ecc6b22", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 70.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "761d52596f76dba5b710", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-30B-A3B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 15.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-30B-A3B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": \"h", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 15.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "93895a6e87e0c82c17d4", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-3.3-70B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 23.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-3.3-70B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Llama 3.3-70B is a multilingual LLM trained on a massive dataset of 15 trillion tokens, fine-tuned for instruction-following and conversational dialogue. The model is designed to be helpful, safe, and flexible, with a focus on responsible deployment and mitigating potential risks such as bias, toxicity, and misinformation. It achieves state-of-the-art performance on ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 23.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0670380e7ffb7a5d213b", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-9B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-9B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-9B is a high-performance model from Alibaba's Qwen3.5 series with a hybrid Gated Delta Networks and sparse MoE architecture. It features a 262K token context window, thinking/reasoning mode, tool calling, multi-token prediction, and support for 201 languages. Excels at reasoning, coding, instruction following, and long-context tasks.\", \"cover_img_url\": \"https://shared.deepinfr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "53ac0ce05a14279aa989", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-5.1", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 105.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-5.1\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"GLM-5.1 is Z-AI's next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/zai-org/GLM-5.1", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 105.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3add2dc84be4edde906e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "openchat/openchat-3.6-8b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openchat/openchat-3.6-8b\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Openchat 3.6 is a LLama-3-8b fine tune that outperforms it on multiple benchmarks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/openchat/openchat-3.6-8b/cover_image.c5792073e4034a0847ff5112e00356adb411c4a5c900ed22c32ad65c5d97e8d1.webp\", \"tags\": [\"openai\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"t", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "e70dbb270b9bc36c1e3d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V4-Flash-0731", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V4-Flash-0731\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V4-Flash-0731 is the official release of DeepSeek-V4-Flash, superseding the preview version, with substantially enhanced agentic capabilities. DeepSeek-V4-Flash-0731 outperforms DeepSeek-V4-Pro (Preview) on benchmarks listed below despite its far smaller activated parameter count, and is broadly competitive with the strongest proprietary models available.\",", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "46d9f4eafc9da3dcaf11", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "ByteDance/Seed-1.8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"ByteDance/Seed-1.8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Optimized specifically for multimodal agent scenarios. It features enhanced agent capabilities, upgraded multimodal comprehension, and more flexible context management.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/ByteDance/Seed-1.8/cover_image.cb600a23d0b2ba7499346c021edb1097501a09cf2a6ee4f0641fd76180624182.webp\", \"tags\": [\"openai\", \"tools\", \"reasoning\", \"multimodal\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "29fcacfeafaf90adde22", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-32B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-32B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3 is the latest generation of large language models in Qwen series, offering a comprehensive suite of dense and mixture-of-experts (MoE) models. Built upon extensive training, Qwen3 delivers groundbreaking advancements in reasoning, instruction-following, agent capabilities, and multilingual support\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-32B/cover_image.", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "406dba9f08dfd3788fca", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "microsoft/Phi-4-multimodal-instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"microsoft/Phi-4-multimodal-instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Phi-4-multimodal-instruct is a lightweight open multimodal foundation model that leverages the language, vision, and speech research and datasets used for Phi-3.5 and 4.0 models. The model processes text, image, and audio inputs, generating text outputs, and comes with 128K token context length. The model underwent an enhancement process, incorporating both supervi", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "97f1d29e860c96a8fe46", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-0.6B-batch", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 0.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-0.6B-batch\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 0.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d817dfd01b73ad33af24", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/QVQ-72B-Preview", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/QVQ-72B-Preview\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"QVQ-72B-Preview is an experimental research model developed by the Qwen team, focusing on enhancing visual reasoning capabilities. QVQ-72B-Preview has achieved remarkable performance on various benchmarks. It scored a remarkable 70.3% on the Multimodal Massive Multi-task Understanding (MMMU) benchmark\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/QVQ-72B-Preview/co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "92835143096048fbda00", "route_provider": "DeepInfra", "model_provider_inferred": "OpenAI", "model_name": "openai/whisper-large-v3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 750.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openai/whisper-large-v3\", \"type\": \"automatic-speech-recognition\", \"reported_type\": \"automatic-speech-recognition\", \"description\": \"Whisper is a general-purpose speech recognition model. It is trained on a large dataset of diverse audio and is also a multi-task model that can perform multilingual speech recognition as well as speech translation and language identification.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/openai/whisper-large-v3/cover_image.fe8f2de15e8bd36b6", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 750.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3078d28b7347204e74f4", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-397B-A17B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 45.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-397B-A17B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-397B-A17B is Alibaba's most capable Qwen3.5 model, a Mixture-of-Experts architecture with 397B total parameters and 17B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling with MCP integration, and support for 201 languages. Sets state-of-the-art results on reasoning, coding, math, and multimod", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 45.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bc2e9f3d6ba79d8235ab", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Devstral-Small-2507", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 7.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Devstral-Small-2507\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Devstral is an agentic LLM for software engineering tasks, making it a great choice for software engineering agents.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Devstral-Small-2507/cover_image.2ca30682c46317e1838d97ea88feffb2e3deecad1e88dfe314351e825fadd56c.webp\", \"tags\": [\"openai\", \"cc-native\", \"tools\"], \"pricing\": {\"discount\": null, \"discount_ends", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 7.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "45162b074a7cce044d79", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2-Thinking", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 47.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2-Thinking\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2 Thinking is the latest, most capable version of open-source thinking model developed by MoonshotAI\", \"cover_img_url\": \"https://shared.deepinfra.com/models/moonshotai/Kimi-K2-Thinking/cover_image.5841c84692f14cc350e7901386cfa0e0e6a49bfd2de40fe12ba89ccfdf6e0a9d.webp\", \"tags\": [\"openai\", \"tools\", \"reasoning\", \"json\", \"structured-output\"], \"pricing\": {\"discount\": null,", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 47.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "11d1abba221a574be4f3", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 30.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Coder-480B-A35B-Instruct-Turbo/cover_image.eda4bf16dbe8f7cb7e0de26", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 30.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "03b81c58e77399efb107", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "microsoft/Phi-3-medium-4k-instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"microsoft/Phi-3-medium-4k-instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Phi-3-Medium-4K-Instruct is a powerful and lightweight language model with 14 billion parameters, trained on high-quality data to excel in instruction following and safety measures. It demonstrates exceptional performance across benchmarks, including common sense, language understanding, and logical reasoning, outperforming models of similar size.\", \"cover_img_u", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b2f1a86eae9cc7af44c7", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "FastVideo/FastWan-QAD-FP8-1.3B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "output_tokens", "component_usd": 0.25, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"FastVideo/FastWan-QAD-FP8-1.3B\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"A fast, compact 480p text-to-video model — 5-second clips (landscape or portrait) from a text prompt. A 3-step, FP8 quantization-aware distillation of Wan2.1-T2V-1.3B by FastVideo (Hao AI Lab).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/FastVideo/FastWan-QAD-FP8-1.3B/cover_image.94fa25fd2ff2bad491428d2849424bc93c8640c97a477a86957265cc6ec5c21d.webp\", \"tags\": [],", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "output_tokens", "amount_usd": 0.25, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0d2103531d4d66525168", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "canopylabs/orpheus-3b-0.1-ft", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 700.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"canopylabs/orpheus-3b-0.1-ft\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"Orpheus TTS is a state-of-the-art, Llama-based Speech-LLM designed for high-quality, empathetic text-to-speech generation. This model has been finetuned to deliver human-level speech synthesis, achieving exceptional clarity, expressiveness, and real-time streaming performances.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/canopylabs/orpheus-3b-0.1-ft/cover_image.", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 700.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a2d3dba8823308290173", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The Llama 4 collection of models are natively multimodal AI models that enable text and multimodal experiences. These models leverage a mixture-of-experts architecture to offer industry-leading performance in text and image understanding. Llama 4 Maverick, a 17 billion parameter model with 128 experts\", \"cover_img_url\": \"https://shared.deepinfra.com/m", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2c56fbe6c26637c8fde0", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-235B-A22B-Instruct-2507", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-235B-A22B-Instruct-2507\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-235B-A22B-Instruct-2507 is the updated version of the Qwen3-235B-A22B non-thinking mode, featuring Significant improvements in general capabilities, including instruction following, logical reasoning, text comprehension, mathematics, science, coding and tool usage. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-235B-A22B-Instruct-2507/cove", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2998ef8ee45315398334", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-3-12b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-3-12b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma 3 introduces multimodality, supporting vision-language input and text outputs. It handles context windows up to 128k tokens, understands over 140 languages, and offers improved math, reasoning, and chat capabilities, including structured outputs and function calling. Gemma 3-12B is Google's latest open source model, successor to Gemma 2\", \"cover_img_url\": \"https://shared.d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b3e4fde08a70fa2a9f6c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-4.6", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-4.6\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Compared with GLM-4.5, GLM-4.6 brings several key improvements: Longer context window: The context window has been expanded from 128K to 200K tokens, enabling the model to handle more complex agentic tasks. Superior coding performance: The model achieves higher scores on code benchmarks and demonstrates better real-world performance in applications such as Claude Code、Cline、Roo Code a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "28ab8aef5a1d07ea49cc", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-VL-32B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-VL-32B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"ocr\", \"openai\", \"multimodal\", \"json\", \"non-reasoning\", \"structured-output\", \"cc-native\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 2e-05, \"cents_per_output_token\": 6e-05, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_wr", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "314207d5126ad109a59e", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemini-3.1-flash-lite", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemini-3.1-flash-lite\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Bring any idea to life with state-of-the-art reasoning to help you learn, build, and plan anything. Best for high-volume tasks that need efficiency and intelligence.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemini-3.1-flash-lite/cover_image.525a90a425f2f2c1855b66bdf94fe2025c945e45e2c724d78a4a4c8d67e1d034.webp\", \"tags\": [\"no-free-anon\", \"cc-native\", \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9498e39c44589e4fb236", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/QwQ-32B-Preview", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 12.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/QwQ-32B-Preview\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"QwQ is an experimental research model developed by the Qwen Team, designed to advance AI reasoning capabilities. This model embodies the spirit of philosophical inquiry, approaching problems with genuine wonder and doubt. QwQ demonstrates impressive analytical abilities, achieving scores of 65.2% on GPQA, 50.0% on AIME, 90.6% on MATH-500, and 50.0% on LiveCodeBench. With its cont", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 12.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "923a034e17a30a94f29d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "deepreinforce-ai/Ornith-1.0-35B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 10.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepreinforce-ai/Ornith-1.0-35B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Ornith-1.0-35B is DeepReinforce's open (MIT-licensed) agentic-coding model: an RL post-train of Qwen3.5-35B-A3B, a 35B-total / ~3B-active Mixture-of-Experts with hybrid Gated-DeltaNet attention. It targets state-of-the-art open-model coding-agent performance (SWE-bench Verified 75.6, Terminal-Bench 2.1 64.2) with a 262K-token context, thinking/reasoning mode, tool call", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 10.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5a13e8bf4f8b92e45f53", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-235B-A22B-Thinking", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 45.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-235B-A22B-Thinking\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 45.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "96ff96f3d7c13abf5924", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2 is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It is optimized for agentic capabilities, including advanced tool use, reasoning, and code synthesis. Kimi K2 excels across a broad range of benchmarks, particularly in coding (LiveCodeBench, SWE-bench), r", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "8879c37271f88c871245", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "PaddlePaddle/PaddleOCR-VL-0.9B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"PaddlePaddle/PaddleOCR-VL-0.9B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"PaddleOCR-VL is a SOTA and resource-efficient model tailored for document parsing. Its core component is PaddleOCR-VL-0.9B, a compact yet powerful vision-language model (VLM) that integrates a NaViT-style dynamic resolution visual encoder with the ERNIE-4.5-0.3B language model to enable accurate element recognition. This innovative model efficiently supports 109 languag", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "899f21577ef60c9dd91b", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Embedding-0.6B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Embedding-0.6B\", \"type\": \"embeddings\", \"reported_type\": \"embeddings\", \"description\": \"The Qwen3 Embedding model series is the latest proprietary model of the Qwen family, specifically designed for text embedding and ranking tasks. Building upon the dense foundational models of the Qwen3 series, it provides a comprehensive range of text embeddings and reranking models in various sizes (0.6B, 4B, and 8B).\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "59e1f931acfbc83bc77c", "route_provider": "DeepInfra", "model_provider_inferred": "OpenAI", "model_name": "openai/gpt-oss-120b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 3.7, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openai/gpt-oss-120b\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"gpt-oss-120b is an open-weight, 117B-parameter Mixture-of-Experts (MoE) language model from OpenAI designed for high-reasoning, agentic, and general-purpose production use cases. The model supports configurable reasoning depth, full chain-of-thought access, and native tool use, including function calling, browsing, and structured output generation.\", \"cover_img_url\": \"https://shar", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 3.7, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "bd9672ba78a1cf3c93cb", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-opus-4-8", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 500.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-opus-4-8\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Opus 4.8 is our most intelligent Opus model and the best generally available model for coding and agents, with deeper reasoning for enterprise workflows.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-opus-4-8/cover_image.7b99143fea9b57c3cd8c35cf3300ce6f5d72e03a79a39f0ae00a3d7bfb264fb0.webp\", \"tags\": [\"multimodal\", \"no-free-anon\", \"structured", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 500.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a7172e34d55446ff5be8", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2.5-Turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 60.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2.5-Turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"openai\", \"tools\", \"reasoning\", \"json\", \"structured-output\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 6e-05, \"cents_per_output_token\": 0.0003, \"rate_per_input_token_cached\": 0.16666667, \"rate_per_input_token_cache_write\": null, \"rate_per_se", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 60.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "7b6ca13297eedf242718", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-fable-5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 1000.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-fable-5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Fable 5 is Anthropic's next generation of intelligence for the hardest knowledge work and coding problems. It works independently for longer than any prior generally available Claude model: run it in an agent harness and it can work for days at a time, planning across stages, delegating to sub-agents, and checking its own work.\", \"cover_img_url\": \"https://shared.deepin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 1000.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9bcc77790927ba6cc933", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-sonnet-4-6", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 300.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-sonnet-4-6\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Sonnet 4.6 delivers frontier intelligence at scale—built for coding, agents, and enterprise workflows.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-sonnet-4-6/cover_image.eb8fe98327537b626c115e8e17b5670154e60083b82bcf56821263f376bb8490.webp\", \"tags\": [\"multimodal\", \"cc-native\", \"reasoning\", \"json\", \"structured-output\", \"tools\", \"ocr\", \"no", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 300.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2ed3e1256188fac0870c", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-2-27b-it", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 27.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-2-27b-it\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is a family of lightweight, state-of-the-art open models from Google. Gemma-2-27B delivers the best performance for its size class, and even offers competitive alternatives to models more than twice its size. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemma-2-27b-it/cover_image.7278882b03ca6732cf6374aaab42734a2ede6343b1b89421f15ad0fc27e3936c.webp\", \"ta", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 27.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "08356dc2dec5b55248ff", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-VL-235B-A22B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 20.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-VL-235B-A22B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meet Qwen3-VL — the most powerful vision-language model in the Qwen series to date. This generation delivers comprehensive upgrades across the board: superior text understanding & generation, deeper visual perception & reasoning, extended context length, enhanced spatial and video dynamics comprehension, and stronger agent interaction capabilities.\", \"cover_img_url\": ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 20.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "17959f061deb979fd41a", "route_provider": "DeepInfra", "model_provider_inferred": "xAI", "model_name": "MiniMaxAI/MiniMax-M2", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 25.400000000000002, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"MiniMaxAI/MiniMax-M2\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"MiniMax-M2 is a Mini model built for Max coding & agentic workflows with just 10 billion activated parameters\", \"cover_img_url\": \"https://shared.deepinfra.com/models/MiniMaxAI/MiniMax-M2/cover_image.5474fbcd5f4eaf2d5123e79bb02291d98597f9b2847a1e2bce182ea836d4d9d5.webp\", \"tags\": [\"openai\", \"cc-native\", \"tools\", \"json\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"shor", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 25.400000000000002, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "2ff731865022e03477d7", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "openbmb/MiniCPM-Llama3-V-2_5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 34.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"openbmb/MiniCPM-Llama3-V-2_5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"\", \"cover_img_url\": \"\", \"tags\": [\"openai\", \"cc-native\", \"multimodal\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": null, \"table\": null, \"type\": \"tokens\", \"cents_per_input_token\": 3.4e-05, \"cents_per_output_token\": 3.4e-05, \"rate_per_input_token_cached\": null, \"rate_per_input_token_cache_write\": null, \"rate_per_service_tier_priority\": nul", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 34.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "037cd59e82e18848e912", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "allenai/olmOCR-7B-0825", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"allenai/olmOCR-7B-0825\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"olmOCR is a specialized AI tool that converts PDF documents into clean, structured text while preserving important formatting and layout information. What makes olmOCR particularly valuable for developers is its ability to handle challenging PDFs that traditional OCR tools struggle with—including complex layouts, poor-quality scans, handwritten text, and documents with mixed co", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "fae84fc972d1fc552924", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2.6", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 75.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2.6\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2.6 is an open-source, native multimodal agentic model that advances practical capabilities in long-horizon coding, coding-driven design, proactive autonomous execution, and swarm-based task orchestration.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/moonshotai/Kimi-K2.6/cover_image.da131f8e266d5af0f8e28c2dcf6575af66977cd4ba0c72ec9147d34b679b5e85.webp\", \"tags\": [", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 75.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "9a68412332606211ec45", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemma-4-31B-it-turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 9.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemma-4-31B-it-turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemma is a family of open models built by Google DeepMind. Gemma 4 models are multimodal, handling text and image input and generating text output.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/google/gemma-4-31B-it-turbo/cover_image.babd01c79288f556de1658963cbee32f654fe7e40863fb389b426390742a8d64.webp\", \"tags\": [\"openai\", \"reasoning\", \"tools\", \"priority\", \"can-d", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 9.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "04eb09f616e40a38073d", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-4-sonnet", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 330.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-4-sonnet\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Anthropic's mid-size model with superior intelligence for high-volume uses in coding, in-depth research, agents, & more.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-4-sonnet/cover_image.abb94fa3840b2f233747c56e1877ad22a139fad1fdd205914141f03a786ca74c.webp\", \"tags\": [\"ocr\", \"openai\", \"tools\", \"multimodal\", \"no-free-anon\", \"json\", \"non-reasoning\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 330.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "c893a442f9248a78c834", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "zai-org/GLM-4.7-Flash", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 6.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"zai-org/GLM-4.7-Flash\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/zai-org/GLM-4.7-Flash/cover_image.3c0c7f830a57de23a3f15107b442a12b8a434b922e45a734dd90791583afd960.webp\", \"tags\": [\"openai\", \"tools\", \"reasonin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 6.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "3935a193e60bcbcd6678", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "sesame/csm-1b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 700.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"sesame/csm-1b\", \"type\": \"text-to-speech\", \"reported_type\": \"text-to-speech\", \"description\": \"CSM (Conversational Speech Model) is a speech generation model from Sesame that generates RVQ audio codes from text and audio inputs. The model architecture employs a Llama backbone and a smaller audio decoder that produces Mimi audio codes.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/sesame/csm-1b/cover_image.e79911aabdd060a3939b5188731bb689a92a627c7e9a0d6e35574937707997ab.we", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 700.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "db09dd90f3b1f691a85c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Sao10K/L3.3-70B-Euryale-v2.3", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 85.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Sao10K/L3.3-70B-Euryale-v2.3\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"L3.3-70B-Euryale-v2.3 is a model focused on creative roleplay from Sao10k\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Sao10K/L3.3-70B-Euryale-v2.3/cover_image.3edd53f864ebe24fe632eaf96361233e514097255cc7ab9bb0d96876aece9a7b.webp\", \"tags\": [\"json\", \"openai\", \"non-reasoning\", \"structured-output\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 85.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "0bfc3ae6a5a745dc8ee1", "route_provider": "DeepInfra", "model_provider_inferred": "Moonshot / Kimi", "model_name": "moonshotai/Kimi-K2-Instruct-0905", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"moonshotai/Kimi-K2-Instruct-0905\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Kimi K2 0905 is the September update of Kimi K2 0711. It is a large-scale Mixture-of-Experts (MoE) language model developed by Moonshot AI, featuring 1 trillion total parameters with 32 billion active per forward pass. It supports long-context inference up to 256k tokens, extended from the previous 128k. This update improves agentic coding with higher accuracy and bet", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "610c779514754b6498f7", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-sonnet-5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 200.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-sonnet-5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Claude Sonnet 5 is Anthropic's most capable Sonnet model yet, built for coding, agents, and professional work at scale. It brings near-Opus intelligence to the model teams run at scale every day, with the same balance of capability, cost, and speed teams already rely on Sonnet for.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-sonnet-5/cover_image.", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 200.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "1a02b3ddaf6d6fdea17d", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/Nemotron-3-Nano-30B-A3B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/Nemotron-3-Nano-30B-A3B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA Nemotron 3 Nano is an open small reasoning model optimized for fast, cost-efficient inference in agentic and production workloads. Built with a hybrid Mixture-of-Experts (MoE) and Mamba-Transformer architecture, it delivers strong multi-step reasoning, high token throughput, stable latency with predictable cost, and efficient deployment for agent-based systems. D", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5797f63abb9b91c01f91", "route_provider": "DeepInfra", "model_provider_inferred": "Google", "model_name": "google/gemini-2.5-pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 125.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"google/gemini-2.5-pro\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Gemini 2.5 Pro is Google's the most advanced thinking model, designed to tackle increasingly complex problems. Gemini 2.5 Pro leads common benchmarks by meaningful margins and showcases strong reasoning and code capabilities. Gemini 2.5 models are thinking models, capable of reasoning through their thoughts before responding, resulting in enhanced performance and improved accura", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 125.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "308eee47b6dc53ba6e96", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "ByteDance/Seedance-1.5-Pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 120.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"ByteDance/Seedance-1.5-Pro\", \"type\": \"text-to-video\", \"reported_type\": \"text-to-video\", \"description\": \"ByteDance's Seedance 1.5 Pro is a professional video model using V2A native generation for integrated, synced audio-visual output, enhancing efficiency of professional video creation.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/ByteDance/Seedance-1.5-Pro/cover_image.3a04465c7b080e6a46070c9ea13aa88e223bb62c44ee8d822f157834af15805d.webp\", \"tags\": [\"no-free-anon\", \"ope", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 120.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "ee7a27ccb0b8ade53a5f", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2-72B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 35.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2-72B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The 72 billion parameter Qwen2 excels in language understanding, multilingual capabilities, coding, mathematics, and reasoning.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen2-72B-Instruct/cover_image.6771b7ff122c6ffaa9d5ae6b6ab54db0d46079a8f90441fa7770d60cfd4c6f4f.webp\", \"tags\": [\"openai\", \"tools\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"s", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 35.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "09515c79e7fff11e324b", "route_provider": "DeepInfra", "model_provider_inferred": "Anthropic", "model_name": "anthropic/claude-haiku-4-5", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 100.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"anthropic/claude-haiku-4-5\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"The next generation of Anthropic's fastest and most cost-effective model, optimal for use cases where speed and affordability matter.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/anthropic/claude-haiku-4-5/cover_image.c2eb61836d5a85e18eed94b3aa6079b8bf3bfe448c801ab7115c210adff90c4d.webp\", \"tags\": [\"json\", \"structured-output\", \"cc-native\", \"reasoning\", \"ocr\", \"ope", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 100.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "27c8e5fbae36dbc8566a", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-Small-3.1-24B-Instruct-2503", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 5.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-Small-3.1-24B-Instruct-2503\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mistral Small 3.1 (2503) adds state-of-the-art vision understanding and extends context capabilities up to 128K tokens while maintaining top-tier text performance. Its 24 billion parameters and instruction fine-tuning deliver fast, local deployment for both text and vision tasks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mistralai/Mistral-Sm", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 5.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "16bee516a3f06aaac8a2", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "nvidia/NVIDIA-Nemotron-3-Super-120B-A12B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 8.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"nvidia/NVIDIA-Nemotron-3-Super-120B-A12B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"NVIDIA Nemotron 3 Super is a hybrid Mixture-of-Experts (MoE) model engineered for highest compute efficiency and accuracy in multi-agent applications and specialized agentic systems. It is optimized to run many collaborating agents per application on a single GPU, delivering high accuracy for reasoning, tool use, and instruction following.\", \"cover_img_url\": \"", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 8.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "fd733d35486af7c9867c", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "ByteDance/Seed-2.0-pro", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 50.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"ByteDance/Seed-2.0-pro\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Built for the Agent era, it delivers stable performance in complex reasoning and long-horizon tasks, including multi-step planning, visual-text reasoning, video understanding, and advanced analysis.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/ByteDance/Seed-2.0-pro/cover_image.a92fa66e5a544f52cfef420dd09a68947530ae0208be1a47cb995c071c48040b.webp\", \"tags\": [\"reasonin", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 50.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "5e778ce8f4847653db37", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-Coder-480B-A35B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 40.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-Coder-480B-A35B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3-Coder-480B-A35B-Instruct is the Qwen3's most agentic code model, featuring Significant Performance on Agentic Coding, Agentic Browser-Use and other foundational coding tasks, achieving results comparable to Claude Sonnet.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Qwen3-Coder-480B-A35B-Instruct/cover_image.d28599e171a40010634df3f9888e4771b4a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 40.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "41bfa5ded5afa36bcf08", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "deepinfra/airoboros-70b", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 70.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepinfra/airoboros-70b\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Latest version of the Airoboros model fine-tunned version of llama-2-70b using the Airoboros dataset. This model is currently running jondurbin/airoboros-l2-70b-2.2.1 \", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepinfra/airoboros-70b/cover_image.4df6a78233488497ec8cad9a032e070a1c2e0c510c7d3b2ebd5c159e15b69793.webp\", \"tags\": [\"openai\", \"json\"], \"pricing\": {\"discou", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 70.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "a53fe6f696d777946315", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Llama-2-70b-chat-hf", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 64.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Llama-2-70b-chat-hf\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"LLaMa 2 is a collections of LLMs trained by Meta. This is the 70B chat optimized version. This endpoint has per token pricing.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Llama-2-70b-chat-hf/cover_image.7b3407408b20bd422edfb75da90ee92d0a05649e94b59bf409c827e845fc3c46.webp\", \"tags\": [\"openai\", \"json\"], \"pricing\": {\"discount\": null, \"discount_ends_a", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 64.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "36d6466085f942a50d19", "route_provider": "DeepInfra", "model_provider_inferred": "DeepInfra", "model_name": "Gryphe/MythoMax-L2-13b-turbo", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 13.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Gryphe/MythoMax-L2-13b-turbo\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Faster version of Gryphe/MythoMax-L2-13b running on multiple H100 cards in fp8 precision. Up to 160 tps. \", \"cover_img_url\": \"https://shared.deepinfra.com/models/Gryphe/MythoMax-L2-13b-turbo/cover_image.1975a8dba4bcf6809a083fe29aff31cb2895a749171f89e0db650bc039da051a.webp\", \"tags\": [\"openai\"], \"pricing\": {\"discount\": null, \"discount_ends_at\": null, \"short\": null, \"full\": ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 13.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "6c7e2091c7536a36830e", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3-0324", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 24.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3-0324\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3-0324, a strong Mixture-of-Experts (MoE) language model with 671B total parameters with 37B activated for each token, an improved iteration over DeepSeek-V3.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V3-0324/cover_image.2132971065034c302886aaa95cfd9661a96989fbe12ec2d93e78ac4c831bf66d.webp\", \"tags\": [\"openai\", \"tools\", \"b200\", ", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 24.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "38621ee99957675ea819", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3-ASR-0.6B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 333.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3-ASR-0.6B\", \"type\": \"automatic-speech-recognition\", \"reported_type\": \"automatic-speech-recognition\", \"description\": \"Qwen3-ASR-0.6B is the compact model of the Qwen3-ASR family: multilingual language identification and speech recognition across 30 languages and 22 Chinese dialects, built on Qwen3-Omni. It targets an accuracy-efficiency trade-off with very high throughput, unified streaming/offline inference, and segment- and word-level timestamps.\", \"cover_img_url\": \"ht", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 333.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "b08043695079339d5c10", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen2.5-Coder-7B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen2.5-Coder-7B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen2.5-Coder-7B is a powerful code-specific large language model with 7.61 billion parameters. It's designed for code generation, reasoning, and fixing tasks. The model covers 92 programming languages and has been trained on 5.5 trillion tokens of data, including source code, text-code grounding, and synthetic data.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/Qwen/Q", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "afd97160f264af5dbcb4", "route_provider": "DeepInfra", "model_provider_inferred": "Mistral AI", "model_name": "mistralai/Mistral-Small-3.2-24B-Instruct-2506", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 7.5, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"mistralai/Mistral-Small-3.2-24B-Instruct-2506\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Mistral-Small-3.2-24B-Instruct is a drop-in upgrade over the 3.1 release, with markedly better instruction following, roughly half the infinite-generation errors, and a more robust function-calling interface—while otherwise matching or slightly improving on all previous text and vision benchmarks.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/mi", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 7.5, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "363556deb713818b1a3c", "route_provider": "DeepInfra", "model_provider_inferred": "Alibaba / Qwen", "model_name": "Qwen/Qwen3.5-35B-A3B", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 14.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"Qwen/Qwen3.5-35B-A3B\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Qwen3.5-35B-A3B is an efficient Mixture-of-Experts model from Alibaba's Qwen3.5 series with 35B total parameters and only 3B activated per token. It features a 262K token context window (extensible to 1M with YaRN), thinking/reasoning mode, tool calling, and support for 201 languages. Delivers strong performance on reasoning, coding, and vision-language tasks at a fraction of the", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": true, "existing_provider_model_match": true, "candidate_use": "coverage_or_crosscheck_signal", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 14.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "de21c54037089dfa20a5", "route_provider": "DeepInfra", "model_provider_inferred": "DeepSeek", "model_name": "deepseek-ai/DeepSeek-V3.2-Exp", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 21.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"deepseek-ai/DeepSeek-V3.2-Exp\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"DeepSeek-V3.2-Exp is an intermediate step toward the next-generation architecture of the DeepSeek models by introducing DeepSeek Sparse Attention—a sparse attention mechanism designed to explore and validate optimizations for training and inference efficiency in long-context scenarios.\", \"cover_img_url\": \"https://shared.deepinfra.com/models/deepseek-ai/DeepSeek-V3.2-Exp/", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 21.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." }, { "candidate_id": "d489fe01ad13d6b477e1", "route_provider": "DeepInfra", "model_provider_inferred": "Meta / Llama", "model_name": "meta-llama/Meta-Llama-3.1-8B-Instruct", "source_id": "deepinfra_models_api", "source_type": "official_api", "source_url": "https://api.deepinfra.com/models/list", "route_type": "direct_provider_api", "currency": "USD", "unit": "1M tokens", "input_usd_per_1m": null, "output_usd_per_1m": null, "component": "input_tokens", "component_usd": 2.0, "confidence": "high", "review_required": true, "promotion_status": "provider_specific_candidate_ready_with_review", "notes_de": "DeepInfra-Modell-/Preiskandidaten. Falls öffentliche API-Felder verfügbar sind, werden diese bevorzugt genutzt.", "notes_en": "DeepInfra model/pricing candidates. Public API fields are preferred when available.", "raw_snippet": "{\"model_name\": \"meta-llama/Meta-Llama-3.1-8B-Instruct\", \"type\": \"text-generation\", \"reported_type\": \"text-generation\", \"description\": \"Meta developed and released the Meta Llama 3.1 family of large language models (LLMs), a collection of pretrained and instruction tuned generative text models in 8B, 70B and 405B sizes\", \"cover_img_url\": \"https://shared.deepinfra.com/models/meta-llama/Meta-Llama-3.1-8B-Instruct/cover_image.bf9600ae0ac92c7da76bb908f82c1fb1ab55c510b637fcc2454e368c7bd1cb72.webp\", \"t", "provider_specific_parser": "deepinfra_models_api_refinement", "provider_specific_parser_version": "2.6.3", "existing_model_name_match": false, "existing_provider_model_match": false, "candidate_use": "possible_new_price_or_route", "provider_specific_checked_at": "2026-08-19T07:06:58+00:00", "provider_specific_provider": "DeepInfra", "provider_specific_note_de": "DeepInfra-API-Kandidaten werden bevorzugt genutzt, weil sie bereits strukturierte Modell-/Preisfelder liefern können.", "provider_specific_note_en": "DeepInfra API candidates are preferred because they can provide structured model/pricing fields.", "provider_specific_model_normalized": true, "provider_specific_components": [ { "component": "input_tokens", "amount_usd": 2.0, "field": "component_usd" } ], "provider_specific_component_count": 1, "provider_specific_token_context": true, "provider_specific_parser_status": "token_candidate_ready", "provider_specific_promotion_readiness": "ready_with_review", "provider_specific_review_required": true, "provider_specific_definition_de": "Anbieterspezifische Zusatzparser normalisieren Modellnamen, Preisbestandteile und Tokenkontext. Die Kandidaten bleiben prüfpflichtig und ersetzen keine Einkaufsfreigabe.", "provider_specific_definition_en": "Provider-specific expansion parsers normalize model names, price components and token context. Candidates remain review-required and do not replace procurement approval." } ] }