{ "models": [ { "name": "GPT-6 Astra", "provider": "openai", "source_key": "gpt-6-astra", "input_cost_per_1m": 10, "output_cost_per_1m": 50, "cache_read_cost_per_1m": 1, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Standard token estimates exclude cache-write surcharges: writes cost $12.50 per MTok, or $25 above 272k prompt tokens. Batch/Flex cost 50% and Fast mode 2x the applicable standard rates.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-6-astra", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-11", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 272k tokens", "max_prompt_tokens": 272000, "input_cost_per_1m": 10, "output_cost_per_1m": 50, "cache_read_cost_per_1m": 1 }, { "id": "long_context", "label": "Prompt above 272k tokens", "min_prompt_tokens": 272001, "input_cost_per_1m": 20, "output_cost_per_1m": 75, "cache_read_cost_per_1m": 2, "note": "Above 272k prompt tokens OpenAI applies 2x input/cache and 1.5x output rates to the full request. Cache-write surcharges are excluded from this estimate." } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GPT-5.6 Sol", "provider": "openai", "source_key": "gpt-5.6-sol", "input_cost_per_1m": 4, "output_cost_per_1m": 20, "cache_read_cost_per_1m": 0.4, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "OpenAI lists promotional pricing of $4 input, $0.40 cached input, and $20 output per MTok through at least November 21, 2026; no exact end date is confirmed. Standard token estimates exclude cache-write surcharges; OpenAI bills cache writes at 1.25x the applicable uncached input rate.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-sol", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-04", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 272k tokens", "max_prompt_tokens": 272000, "input_cost_per_1m": 4, "output_cost_per_1m": 20, "cache_read_cost_per_1m": 0.4 }, { "id": "long_context", "label": "Prompt above 272k tokens", "min_prompt_tokens": 272001, "input_cost_per_1m": 8, "output_cost_per_1m": 30, "cache_read_cost_per_1m": 0.8, "note": "OpenAI documents 2x input and 1.5x output above 272k prompt tokens; the cached-input rate is derived with the documented 2x input multiplier." } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GPT-5.6 Terra", "provider": "openai", "source_key": "gpt-5.6-terra", "input_cost_per_1m": 2, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 0.2, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Standard token estimates exclude cache-write surcharges; OpenAI bills cache writes at 1.25x the applicable uncached input rate.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-terra", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-04", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 272k tokens", "max_prompt_tokens": 272000, "input_cost_per_1m": 2, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt above 272k tokens", "min_prompt_tokens": 272001, "input_cost_per_1m": 4, "output_cost_per_1m": 18, "cache_read_cost_per_1m": 0.4, "note": "Cached-input rate is derived with OpenAI's documented 2x input multiplier." } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GPT-5.6 Luna", "provider": "openai", "source_key": "gpt-5.6-luna", "input_cost_per_1m": 0.2, "output_cost_per_1m": 1.2, "cache_read_cost_per_1m": 0.02, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "budget", "fast", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "budget", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Standard token estimates exclude cache-write surcharges; OpenAI bills cache writes at 1.25x the applicable uncached input rate.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-5.6-luna", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-04", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 272k tokens", "max_prompt_tokens": 272000, "input_cost_per_1m": 0.2, "output_cost_per_1m": 1.2, "cache_read_cost_per_1m": 0.02 }, { "id": "long_context", "label": "Prompt above 272k tokens", "min_prompt_tokens": 272001, "input_cost_per_1m": 0.4, "output_cost_per_1m": 1.8, "cache_read_cost_per_1m": 0.04, "note": "Cached-input rate is derived with OpenAI's documented 2x input multiplier." } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GPT-5.5", "provider": "openai", "source_key": "gpt-5.5", "input_cost_per_1m": 5, "output_cost_per_1m": 30, "cache_read_cost_per_1m": 0.5, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-5.5", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 272k tokens", "max_prompt_tokens": 272000, "input_cost_per_1m": 5, "output_cost_per_1m": 30, "cache_read_cost_per_1m": 0.5 }, { "id": "long_context", "label": "Prompt above 272k tokens", "min_prompt_tokens": 272001, "input_cost_per_1m": 10, "output_cost_per_1m": 45, "cache_read_cost_per_1m": 1, "note": "OpenAI documents 2x input and 1.5x output above 272k prompt tokens; the cached-input rate is derived with the documented 2x input multiplier." } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GPT-5.5 Pro", "provider": "openai", "source_key": "gpt-5.5-pro", "input_cost_per_1m": 30, "output_cost_per_1m": 180, "cache_read_cost_per_1m": 30, "context_window": 1050000, "max_output_tokens": 128000, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.openai.com/api/docs/models/gpt-5.5-pro", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Opus 4.7", "provider": "anthropic", "source_key": "claude-opus-4-7", "input_cost_per_1m": 5, "output_cost_per_1m": 25, "cache_read_cost_per_1m": 0.5, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Opus 4.8", "provider": "anthropic", "source_key": "claude-opus-4-8", "input_cost_per_1m": 5, "output_cost_per_1m": 25, "cache_read_cost_per_1m": 0.5, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Opus 5", "provider": "anthropic", "source_key": "claude-opus-5", "input_cost_per_1m": 5, "output_cost_per_1m": 25, "cache_read_cost_per_1m": 0.5, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Anthropic lists Claude Opus 5 as generally available since 2026-07-24 with 1M context and 128k maximum output.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Mythos 5", "provider": "anthropic", "source_key": "claude-mythos-5", "input_cost_per_1m": 10, "output_cost_per_1m": 50, "cache_read_cost_per_1m": 1, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly", "mythos-class", "limited-availability" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "limited_availability", "availability_note": "Anthropic describes Claude Mythos 5 as limited availability for approved Project Glasswing customers, not general public routing.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Mythos 5.1", "provider": "anthropic", "source_key": "claude-mythos-5-1", "input_cost_per_1m": 10, "output_cost_per_1m": 50, "cache_read_cost_per_1m": 0.25, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "premium", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly", "mythos-class", "limited-availability" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "limited_availability", "availability_note": "Anthropic released Claude Mythos 5.1 on September 1, 2026 as an invite-only Project Glasswing model for vetted organizations; it is not eligible for default public routing.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/models/mythos-5-1/overview", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-02", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Sonnet 5", "provider": "anthropic", "source_key": "claude-sonnet-5", "input_cost_per_1m": 2, "output_cost_per_1m": 10, "cache_read_cost_per_1m": 0.2, "context_window": 1000000, "max_output_tokens": 128000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "coding", "agents", "enterprise-rag", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Anthropic now lists the introductory $2 input, $0.20 cached input, and $10 output per MTok rates as the permanent standard price; the previously announced September 1 increase will not occur.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1.3, "tokenizer_note": "Anthropic states the newer tokenizer may produce about 30% more tokens for many workloads; this multiplier is only a planning estimate.", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Claude Haiku 4.5", "provider": "anthropic", "source_key": "claude-haiku-4-5", "input_cost_per_1m": 1, "output_cost_per_1m": 5, "cache_read_cost_per_1m": 0.1, "context_window": 200000, "max_output_tokens": 64000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "fast", "budget", "agents", "enterprise-rag", "cache-friendly" ], "model_groups": [ "budget", "rag" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://platform.claude.com/docs/en/about-claude/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.1 Pro Preview", "provider": "gemini", "source_key": "gemini-3.1-pro-preview", "input_cost_per_1m": 2, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 0.2, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "preview", "reasoning", "long-context", "multimodal", "enterprise-rag" ], "model_groups": [ "frontier", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-22", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt up to 200k tokens", "max_prompt_tokens": 200000, "input_cost_per_1m": 2, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt above 200k tokens", "min_prompt_tokens": 200001, "input_cost_per_1m": 4, "output_cost_per_1m": 18, "cache_read_cost_per_1m": 0.4 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.8 Flash", "provider": "gemini", "source_key": "gemini-3.8-flash", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "fast", "reasoning", "long-context", "multimodal", "cache-friendly", "stable" ], "model_groups": [ "frontier", "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Google released Gemini 3.8 Flash as generally available on September 2026, with introductory pricing through December 31, 2026.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.8-flash", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-04", "pricing_periods": [ { "id": "introductory_pricing", "ends_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075 }, { "id": "standard_after_introductory_pricing", "starts_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 1.5, "output_cost_per_1m": 7.5, "cache_read_cost_per_1m": 0.15 } ], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.7 Flash", "provider": "gemini", "source_key": "gemini-3.7-flash", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "fast", "reasoning", "long-context", "multimodal", "cache-friendly", "stable" ], "model_groups": [ "frontier", "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Google released Gemini 3.7 Flash as generally available on August 13, 2026, with introductory pricing through December 31, 2026.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.7-flash", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-19", "pricing_periods": [ { "id": "introductory_pricing", "ends_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075 }, { "id": "standard_after_introductory_pricing", "starts_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 1.5, "output_cost_per_1m": 7.5, "cache_read_cost_per_1m": 0.15 } ], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.6 Flash", "provider": "gemini", "source_key": "gemini-3.6-flash", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "fast", "reasoning", "long-context", "multimodal", "cache-friendly", "stable" ], "model_groups": [ "frontier", "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Google applies the Gemini 3.7 Flash introductory rate to Gemini 3.6 Flash through December 31, 2026; standard pricing resumes January 1, 2027.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.6-flash", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-21", "pricing_periods": [ { "id": "introductory_pricing", "ends_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 0.75, "output_cost_per_1m": 3.75, "cache_read_cost_per_1m": 0.075 }, { "id": "standard_after_introductory_pricing", "starts_at": "2027-01-01T00:00:00Z", "input_cost_per_1m": 1.5, "output_cost_per_1m": 7.5, "cache_read_cost_per_1m": 0.15 } ], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.5 Flash", "provider": "gemini", "source_key": "gemini-3.5-flash", "input_cost_per_1m": 1.5, "output_cost_per_1m": 9, "cache_read_cost_per_1m": 0.15, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "fast", "reasoning", "long-context", "multimodal", "cache-friendly", "stable" ], "model_groups": [ "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-22", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.5 Flash-Lite", "provider": "gemini", "source_key": "gemini-3.5-flash-lite", "input_cost_per_1m": 0.3, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.03, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "budget", "fast", "high-volume", "long-context", "multimodal", "cache-friendly", "stable" ], "model_groups": [ "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-22", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Gemini 3.1 Flash-Lite", "provider": "gemini", "source_key": "gemini/gemini-3.1-flash-lite", "input_cost_per_1m": 0.25, "output_cost_per_1m": 1.5, "cache_read_cost_per_1m": 0.025, "context_window": 1048576, "max_output_tokens": 65536, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "budget", "fast", "high-volume", "stable", "multimodal", "cache-friendly" ], "model_groups": [ "budget", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://ai.google.dev/gemini-api/docs/pricing#gemini-3.1-flash-lite", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-19", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "DeepSeek V4.1 Flash", "provider": "deepseek", "source_key": "deepseek-flash", "input_cost_per_1m": 0.3, "output_cost_per_1m": 1.2, "cache_read_cost_per_1m": 0.006, "context_window": 1000000, "max_output_tokens": 384000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "budget", "high-volume", "coding", "reasoning", "long-context", "cache-friendly", "multimodal" ], "model_groups": [ "budget", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "DeepSeek retired the V4 Flash and V4 Flash Vision Exp model versions; their legacy IDs now serve V4.1 Flash. The calculator uses the conservative peak tariff. Off-peak rates are $0.15 input, $0.003 cached input, and $0.60 output per MTok outside the weekday peak windows 01:00-04:00 and 06:00-10:00 UTC; weekends are entirely off-peak.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://api-docs.deepseek.com/quick_start/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "DeepSeek V4 Pro", "provider": "deepseek", "source_key": "deepseek-v4-pro", "input_cost_per_1m": 1.32, "output_cost_per_1m": 3.96, "cache_read_cost_per_1m": 0.044, "context_window": 1000000, "max_output_tokens": 384000, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "frontier", "premium", "coding", "reasoning", "agents", "open-weight", "long-context", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "DeepSeek continues to provide V4 Pro after September 14, 2026 with unchanged billing. The calculator uses the conservative peak tariff. Off-peak rates are $0.66 input, $0.022 cached input, and $1.98 output per MTok outside the weekday peak windows 01:00-04:00 and 06:00-10:00 UTC; weekends are entirely off-peak.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://api-docs.deepseek.com/quick_start/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GLM-5.2", "provider": "cloudflare", "source_key": "glm-5.2", "input_cost_per_1m": 1.4, "output_cost_per_1m": 4.4, "cache_read_cost_per_1m": 0.26, "context_window": 262144, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "open-weight", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.cloudflare.com/workers-ai/models/glm-5.2/", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-21", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GLM-5.3", "provider": "cloudflare", "source_key": "glm-5.3", "input_cost_per_1m": 1.4, "output_cost_per_1m": 4.4, "cache_read_cost_per_1m": 0.26, "context_window": 1048576, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "open-weight", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Cloudflare lists GLM-5.3 as paid-only on Workers AI. No separate maximum output limit is documented.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.cloudflare.com/workers-ai/models/glm-5.3/", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-31", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "GLM-5.3 Flash", "provider": "cloudflare", "source_key": "glm-5.3-flash", "input_cost_per_1m": 0.15, "output_cost_per_1m": 0.5, "cache_read_cost_per_1m": 0.03, "context_window": 1048576, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "budget", "reasoning", "coding", "agents", "long-context", "multimodal", "open-weight", "cache-friendly" ], "model_groups": [ "frontier", "budget", "coding", "rag", "local-open", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Cloudflare lists GLM-5.3 Flash as paid-only on Workers AI. Ollama currently exposes only a cloud tag, so it is not treated as a local Ollama model.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://developers.cloudflare.com/workers-ai/models/glm-5.3-flash/", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-28", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok Build 0.1", "provider": "xai", "source_key": "grok-build-0.1", "input_cost_per_1m": 1, "output_cost_per_1m": 2, "cache_read_cost_per_1m": 0.2, "context_window": 256000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "budget", "coding", "reasoning", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "budget", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "xAI lists Grok Build 0.1 as an agentic coding model. No separate maximum output limit is documented.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/models/grok-build-0.1", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-11", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 1, "output_cost_per_1m": 2, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 2, "output_cost_per_1m": 4, "cache_read_cost_per_1m": 0.4 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok 4.6", "provider": "xai", "source_key": "grok-4.6", "input_cost_per_1m": 2, "output_cost_per_1m": 6, "cache_read_cost_per_1m": 0.5, "context_window": 500000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/models/grok-4.6", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-24", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 2, "output_cost_per_1m": 6, "cache_read_cost_per_1m": 0.5 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 4, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 1 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok 4.5", "provider": "xai", "source_key": "grok-4.5", "input_cost_per_1m": 2, "output_cost_per_1m": 6, "cache_read_cost_per_1m": 0.3, "context_window": 500000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-24", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 2, "output_cost_per_1m": 6, "cache_read_cost_per_1m": 0.3 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 4, "output_cost_per_1m": 12, "cache_read_cost_per_1m": 0.6 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok 4.3", "provider": "xai", "source_key": "grok-4.3", "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2, "context_window": 1000000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "coding", "agents", "long-context", "multimodal", "cache-friendly" ], "model_groups": [ "frontier", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "xAI lists Grok 4.3 as a generally available multimodal model with configurable reasoning. No separate maximum output limit is documented.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/models/grok-4.3", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-14", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 2.5, "output_cost_per_1m": 5, "cache_read_cost_per_1m": 0.4 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok 4.20 Reasoning", "provider": "xai", "source_key": "grok-4.20-0309-reasoning", "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2, "context_window": 1000000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "reasoning", "agents", "long-context", "multimodal" ], "model_groups": [ "frontier", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-24", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 2.5, "output_cost_per_1m": 5, "cache_read_cost_per_1m": 0.4 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Grok 4.20 Multi-Agent", "provider": "xai", "source_key": "grok-4.20-multi-agent-0309", "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2, "context_window": 1000000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "multi-agent", "agents", "reasoning", "long-context" ], "model_groups": [ "frontier", "rag" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.x.ai/developers/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-24", "pricing_periods": [], "pricing_tiers": [ { "id": "standard", "label": "Prompt below 200k tokens", "max_prompt_tokens": 199999, "input_cost_per_1m": 1.25, "output_cost_per_1m": 2.5, "cache_read_cost_per_1m": 0.2 }, { "id": "long_context", "label": "Prompt from 200k tokens", "min_prompt_tokens": 200000, "input_cost_per_1m": 2.5, "output_cost_per_1m": 5, "cache_read_cost_per_1m": 0.4 } ], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Qwen3.6 Plus", "provider": "openrouter", "source_key": "openrouter/qwen/qwen3.6-plus", "input_cost_per_1m": 0.325, "output_cost_per_1m": 1.95, "cache_read_cost_per_1m": 0, "context_window": 1000000, "max_output_tokens": 65536, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "coding", "reasoning", "open-weight", "budget" ], "model_groups": [ "coding", "local-open", "budget" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://openrouter.ai/api/v1/models", "pricing_source_type": "aggregated_provider_metadata", "verification_status": "aggregated", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Qwen3 Max", "provider": "novita", "source_key": "novita/qwen/qwen3-max", "input_cost_per_1m": 2.11, "output_cost_per_1m": 8.45, "cache_read_cost_per_1m": 0, "context_window": 262144, "max_output_tokens": 65536, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "frontier", "coding", "reasoning", "agents", "open-weight" ], "model_groups": [ "frontier", "coding", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://raw.githubusercontent.com/BerriAI/litellm/main/model_prices_and_context_window.json", "pricing_source_type": "aggregated_provider_metadata", "verification_status": "aggregated", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Mistral Small 4", "provider": "mistral", "source_key": "mistral/mistral-small-2603", "input_cost_per_1m": 0.15, "output_cost_per_1m": 0.6, "cache_read_cost_per_1m": 0.015, "context_window": 256000, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "budget", "coding", "reasoning", "agents", "open-weight", "enterprise", "multimodal" ], "model_groups": [ "budget", "coding", "rag", "local-open", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "Mistral documents a 256k context window and image input, but no separate maximum output limit.", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.mistral.ai/models/mistral-small-4-0-26-03", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-09-11", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Mistral Large 3", "provider": "mistral", "source_key": "mistral/mistral-large-3", "input_cost_per_1m": 0.5, "output_cost_per_1m": 1.5, "cache_read_cost_per_1m": 0.05, "context_window": 262144, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "coding", "reasoning", "agents", "open-weight", "enterprise" ], "model_groups": [ "frontier", "coding", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.mistral.ai/inference/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-21", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Mistral Medium 3.5", "provider": "mistral", "source_key": "mistral/mistral-medium-3-5", "input_cost_per_1m": 1.5, "output_cost_per_1m": 7.5, "cache_read_cost_per_1m": 0.15, "context_window": 262144, "max_output_tokens": null, "supports_prompt_caching": true, "supports_function_calling": true, "supports_vision": true, "category_tags": [ "frontier", "coding", "reasoning", "agents", "multimodal", "open-weight", "enterprise" ], "model_groups": [ "frontier", "coding", "rag", "multimodal", "local-open" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.mistral.ai/inference/pricing", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-21", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Cohere Command A", "provider": "cohere_chat", "source_key": "command-a-03-2025", "input_cost_per_1m": 2.5, "output_cost_per_1m": 10, "cache_read_cost_per_1m": 0, "context_window": 256000, "max_output_tokens": 8000, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "enterprise-rag", "rag", "long-context", "agents" ], "model_groups": [ "rag" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.cohere.com/docs/command-a", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-08-19", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Cohere Command R7B", "provider": "cohere_chat", "source_key": "command-r7b-12-2024", "input_cost_per_1m": 0.0375, "output_cost_per_1m": 0.15, "cache_read_cost_per_1m": 0, "context_window": 128000, "max_output_tokens": 4000, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "budget", "high-volume", "enterprise-rag", "rag" ], "model_groups": [ "budget", "rag" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://docs.cohere.com/docs/command-r7b", "pricing_source_type": "official_provider", "verification_status": "verified", "last_verified_at": "2026-07-24", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Llama 4 Maverick", "provider": "deepinfra", "source_key": "deepinfra/meta-llama/Llama-4-Maverick-17B-128E-Instruct-FP8", "input_cost_per_1m": 0.2, "output_cost_per_1m": 0.8, "cache_read_cost_per_1m": 0, "context_window": 1048576, "max_output_tokens": 1048576, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "open-weight", "coding", "agents", "multimodal", "long-context" ], "model_groups": [ "local-open", "coding", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://deepinfra.com/pricing", "pricing_source_type": "aggregated_provider_metadata", "verification_status": "aggregated", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" }, { "name": "Llama 4 Scout", "provider": "deepinfra", "source_key": "deepinfra/meta-llama/Llama-4-Scout-17B-16E-Instruct", "input_cost_per_1m": 0.1, "output_cost_per_1m": 0.3, "cache_read_cost_per_1m": 0, "context_window": 327680, "max_output_tokens": 327680, "supports_prompt_caching": false, "supports_function_calling": true, "supports_vision": false, "category_tags": [ "budget", "high-volume", "open-weight", "multimodal", "long-context" ], "model_groups": [ "budget", "local-open", "rag", "multimodal" ], "pricing_status": "active", "availability_status": "generally_available", "availability_note": "", "pricing_policy": "exclude_if_missing_price", "pricing_source_url": "https://deepinfra.com/pricing", "pricing_source_type": "aggregated_provider_metadata", "verification_status": "aggregated", "last_verified_at": "2026-09-18", "pricing_periods": [], "pricing_tiers": [], "tokenizer_estimate_multiplier": 1, "tokenizer_note": "", "snapshot_generated_at": "2026-09-18T07:16:01.853Z", "last_checked_at": "2026-09-18T07:16:01.853Z" } ] }