{
 "title": "State of LLM API Pricing 2026",
 "url": "https://litmiq.com/llm-api-pricing",
 "publisher": "Litmiq",
 "license": "CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/)",
 "checked": "2026-11-12",
 "units": "USD per 1 million tokens, standard (non-batch) tier, list prices as shown on each provider's official pricing page",
 "notes": "cached_input_per_1m_usd is null where the source page row we used does not show a cached price (it is NOT zero). cost_per_conversation_usd is Litmiq's arithmetic using the disclosed assumptions below.",
 "calculator_assumptions": {
  "system_tokens": 2000,
  "user_tokens": 60,
  "reply_tokens": 150,
  "turns": 4,
  "input_tokens_per_conversation": 9500,
  "output_tokens_per_conversation": 600,
  "formula": "turn k input = system + k*user + (k-1)*reply; cost = (input_tokens*input_price + output_tokens*output_price)/1,000,000"
 },
 "provider_notes": {
  "OpenAI": "Batch API is 50% off. Models released on or after March 5, 2026 add a 10% uplift for regional processing.",
  "Anthropic": "Batch is 50% off. Claude 4.7 and later use a tokenizer that produces approximately 30% more tokens for the same text.",
  "Google": "Output prices include thinking tokens.",
  "Mistral": "mistral.ai/pricing FAQ: 'Mistral Large costs $0.5 /M tokens in and $1.5 /M tokens out', which differs from the Mistral Large 4 model page ($0.7 / $2.1). We use the model page and flag the gap."
 },
 "sources": {
  "OpenAI": "https://developers.openai.com/api/docs/pricing",
  "Anthropic": "https://platform.claude.com/docs/en/about-claude/pricing",
  "Google": "https://ai.google.dev/gemini-api/docs/pricing",
  "DeepSeek": "https://api-docs.deepseek.com/quick_start/pricing",
  "xAI": "https://docs.x.ai/docs/models",
  "Mistral": "https://docs.mistral.ai/models/",
  "Cloudflare Workers AI": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
  "Groq": "https://console.groq.com/docs/models",
  "Together AI": "https://www.together.ai/pricing"
 },
 "price_changes": [
  {
   "provider": "Google",
   "model": "Gemini 4 Carbon / Gemini 4 Argon",
   "date": "2026-12-01",
   "before": "$2.00 / $10.00",
   "after": "$4.00 / $20.00",
   "kind": "Scheduled increase",
   "source": "https://ai.google.dev/gemini-api/docs/pricing"
  },
  {
   "provider": "Google",
   "model": "Gemini 3.8 Flash / Gemini 3.6 Flash",
   "date": "2027-01-01",
   "before": "$0.75 / $3.75",
   "after": "$1.50 / $7.50",
   "kind": "Scheduled increase",
   "source": "https://ai.google.dev/gemini-api/docs/pricing"
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.6-sol",
   "date": "2026-11-30",
   "before": "$4 / $20 (promotional)",
   "after": "Not disclosed on the page",
   "kind": "Promotion ends",
   "source": "https://developers.openai.com/api/docs/pricing"
  },
  {
   "provider": "Anthropic",
   "model": "Claude Sonnet 5",
   "date": "2026-09-01",
   "before": "$2 / $10 (introductory)",
   "after": "$2 / $10 (now standard; planned $3 / $15 cancelled)",
   "kind": "Planned increase cancelled",
   "source": "https://platform.claude.com/docs/en/about-claude/pricing"
  },
  {
   "provider": "OpenAI",
   "model": "All models (Priority processing)",
   "date": "2026-07-30",
   "before": "Priority processing",
   "after": "Renamed Fast mode",
   "kind": "Tier renamed",
   "source": "https://developers.openai.com/api/docs/pricing"
  },
  {
   "provider": "DeepSeek",
   "model": "deepseek-flash, deepseek-v4-pro",
   "date": "",
   "before": "Peak price",
   "after": "50% off outside peak hours (01:00-04:00 and 06:00-10:00 UTC, Mon-Fri are peak)",
   "kind": "Time-of-day pricing",
   "source": "https://api-docs.deepseek.com/quick_start/pricing"
  }
 ],
 "anthropic_opus_generations": [
  {
   "model": "Opus 4 / 4.1",
   "input": 15,
   "output": 75
  },
  {
   "model": "Opus 4.5 to 5",
   "input": 5,
   "output": 25
  },
  {
   "model": "Opus 5.5",
   "input": 4,
   "output": 20
  }
 ],
 "models": [
  {
   "provider": "OpenAI",
   "model": "gpt-6-astra",
   "input_per_1m_usd": 10,
   "output_per_1m_usd": 50,
   "cached_input_per_1m_usd": 1.0,
   "notes": "Standard tier, short context (<=272K input)",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.125,
   "cost_per_10k_conversations_usd": 1250.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-6.1-sol",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": 0.1,
   "notes": "Standard tier, short context",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-6.1-terra",
   "input_per_1m_usd": 1,
   "output_per_1m_usd": 5,
   "cached_input_per_1m_usd": 0.05,
   "notes": "Standard tier, short context",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0125,
   "cost_per_10k_conversations_usd": 125.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-6-luna",
   "input_per_1m_usd": 0.1,
   "output_per_1m_usd": 0.5,
   "cached_input_per_1m_usd": 0.01,
   "notes": "Standard tier, short context",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00125,
   "cost_per_10k_conversations_usd": 12.5
  },
  {
   "provider": "OpenAI",
   "model": "gpt-6-sol",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": 0.2,
   "notes": "Standard tier, short context",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.6-sol",
   "input_per_1m_usd": 4,
   "output_per_1m_usd": 20,
   "cached_input_per_1m_usd": null,
   "notes": "Promotional pricing available until November 30, 2026 (per page)",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.05,
   "cost_per_10k_conversations_usd": 500.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.6-terra",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 12,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0262,
   "cost_per_10k_conversations_usd": 262.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.6-luna",
   "input_per_1m_usd": 0.2,
   "output_per_1m_usd": 1.2,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00262,
   "cost_per_10k_conversations_usd": 26.2
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.5",
   "input_per_1m_usd": 5,
   "output_per_1m_usd": 30,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0655,
   "cost_per_10k_conversations_usd": 655.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.5-pro",
   "input_per_1m_usd": 30,
   "output_per_1m_usd": 180,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.393,
   "cost_per_10k_conversations_usd": 3930.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.4",
   "input_per_1m_usd": 2.5,
   "output_per_1m_usd": 15,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.03275,
   "cost_per_10k_conversations_usd": 327.5
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.4-mini",
   "input_per_1m_usd": 0.75,
   "output_per_1m_usd": 4.5,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.009825,
   "cost_per_10k_conversations_usd": 98.25
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.4-nano",
   "input_per_1m_usd": 0.2,
   "output_per_1m_usd": 1.25,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00265,
   "cost_per_10k_conversations_usd": 26.5
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.2",
   "input_per_1m_usd": 1.75,
   "output_per_1m_usd": 14,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025025,
   "cost_per_10k_conversations_usd": 250.25
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5.1",
   "input_per_1m_usd": 1.25,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.017875,
   "cost_per_10k_conversations_usd": 178.75
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5",
   "input_per_1m_usd": 1.25,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.017875,
   "cost_per_10k_conversations_usd": 178.75
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5-mini",
   "input_per_1m_usd": 0.25,
   "output_per_1m_usd": 2,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.003575,
   "cost_per_10k_conversations_usd": 35.75
  },
  {
   "provider": "OpenAI",
   "model": "gpt-5-nano",
   "input_per_1m_usd": 0.05,
   "output_per_1m_usd": 0.4,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000715,
   "cost_per_10k_conversations_usd": 7.15
  },
  {
   "provider": "OpenAI",
   "model": "gpt-4.1",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 8,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0238,
   "cost_per_10k_conversations_usd": 238.0
  },
  {
   "provider": "OpenAI",
   "model": "gpt-4.1-mini",
   "input_per_1m_usd": 0.4,
   "output_per_1m_usd": 1.6,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00476,
   "cost_per_10k_conversations_usd": 47.6
  },
  {
   "provider": "OpenAI",
   "model": "gpt-4o",
   "input_per_1m_usd": 2.5,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.02975,
   "cost_per_10k_conversations_usd": 297.5
  },
  {
   "provider": "OpenAI",
   "model": "gpt-4o-mini",
   "input_per_1m_usd": 0.15,
   "output_per_1m_usd": 0.6,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.001785,
   "cost_per_10k_conversations_usd": 17.85
  },
  {
   "provider": "OpenAI",
   "model": "o3",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 8,
   "cached_input_per_1m_usd": null,
   "notes": "Standard tier",
   "source_url": "https://developers.openai.com/api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0238,
   "cost_per_10k_conversations_usd": 238.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Fable 5.2",
   "input_per_1m_usd": 8,
   "output_per_1m_usd": 40,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output (same price listed for Mythos 5.2)",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.1,
   "cost_per_10k_conversations_usd": 1000.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Fable 5.1",
   "input_per_1m_usd": 10,
   "output_per_1m_usd": 50,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.125,
   "cost_per_10k_conversations_usd": 1250.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Opus 5.5",
   "input_per_1m_usd": 4,
   "output_per_1m_usd": 20,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.05,
   "cost_per_10k_conversations_usd": 500.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Opus 5",
   "input_per_1m_usd": 5,
   "output_per_1m_usd": 25,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output (same as Opus 4.5-4.8)",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0625,
   "cost_per_10k_conversations_usd": 625.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Opus 4.5",
   "input_per_1m_usd": 5,
   "output_per_1m_usd": 25,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0625,
   "cost_per_10k_conversations_usd": 625.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Opus 4.1",
   "input_per_1m_usd": 15,
   "output_per_1m_usd": 75,
   "cached_input_per_1m_usd": null,
   "notes": "Listed as retired",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.1875,
   "cost_per_10k_conversations_usd": 1875.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Sonnet 5.5",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Sonnet 5",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 10,
   "cached_input_per_1m_usd": null,
   "notes": "Introductory price made standard; planned rise to $3/$15 on Sep 1, 2026 will not occur",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Sonnet 4.6",
   "input_per_1m_usd": 3,
   "output_per_1m_usd": 15,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output (same as Sonnet 4.5 and 4)",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0375,
   "cost_per_10k_conversations_usd": 375.0
  },
  {
   "provider": "Anthropic",
   "model": "Claude Haiku 5.5",
   "input_per_1m_usd": 0.1,
   "output_per_1m_usd": 0.5,
   "cached_input_per_1m_usd": null,
   "notes": "Prompts <=100k tokens; $0.50/$2.50 above 100k",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00125,
   "cost_per_10k_conversations_usd": 12.5
  },
  {
   "provider": "Anthropic",
   "model": "Claude Haiku 4.5",
   "input_per_1m_usd": 1,
   "output_per_1m_usd": 5,
   "cached_input_per_1m_usd": null,
   "notes": "Base input / output",
   "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0125,
   "cost_per_10k_conversations_usd": 125.0
  },
  {
   "provider": "Google",
   "model": "Gemini 4 Carbon",
   "input_per_1m_usd": 2.0,
   "output_per_1m_usd": 10.0,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier through Nov 30, 2026; $4/$20 from Dec 1, 2026",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "Google",
   "model": "Gemini 4 Argon",
   "input_per_1m_usd": 2.0,
   "output_per_1m_usd": 10.0,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier through Nov 30, 2026; $4/$20 from Dec 1, 2026",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.025,
   "cost_per_10k_conversations_usd": 250.0
  },
  {
   "provider": "Google",
   "model": "Gemini 4 Hydrogen",
   "input_per_1m_usd": 1.5,
   "output_per_1m_usd": 7.5,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.01875,
   "cost_per_10k_conversations_usd": 187.5
  },
  {
   "provider": "Google",
   "model": "Gemini 3.8 Flash",
   "input_per_1m_usd": 0.75,
   "output_per_1m_usd": 3.75,
   "cached_input_per_1m_usd": null,
   "notes": "Through Dec 31, 2026; $1.50/$7.50 from Jan 1, 2027",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.009375,
   "cost_per_10k_conversations_usd": 93.75
  },
  {
   "provider": "Google",
   "model": "Gemini 3.6 Flash",
   "input_per_1m_usd": 0.75,
   "output_per_1m_usd": 3.75,
   "cached_input_per_1m_usd": null,
   "notes": "Through Dec 31, 2026; $1.50/$7.50 from Jan 1, 2027",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.009375,
   "cost_per_10k_conversations_usd": 93.75
  },
  {
   "provider": "Google",
   "model": "Gemini 3.5 Flash-Lite",
   "input_per_1m_usd": 0.3,
   "output_per_1m_usd": 2.5,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00435,
   "cost_per_10k_conversations_usd": 43.5
  },
  {
   "provider": "Google",
   "model": "Gemini 3.1 Pro Preview",
   "input_per_1m_usd": 2.0,
   "output_per_1m_usd": 12.0,
   "cached_input_per_1m_usd": null,
   "notes": "Prompts <=200k; $4/$18 above 200k",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0262,
   "cost_per_10k_conversations_usd": 262.0
  },
  {
   "provider": "Google",
   "model": "Gemini 3.1 Flash-Lite",
   "input_per_1m_usd": 0.25,
   "output_per_1m_usd": 1.5,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.003275,
   "cost_per_10k_conversations_usd": 32.75
  },
  {
   "provider": "Google",
   "model": "Gemini 3 Flash Preview",
   "input_per_1m_usd": 0.5,
   "output_per_1m_usd": 3.0,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00655,
   "cost_per_10k_conversations_usd": 65.5
  },
  {
   "provider": "Google",
   "model": "Gemini 2.5 Pro",
   "input_per_1m_usd": 1.25,
   "output_per_1m_usd": 10.0,
   "cached_input_per_1m_usd": null,
   "notes": "Prompts <=200k",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.017875,
   "cost_per_10k_conversations_usd": 178.75
  },
  {
   "provider": "Google",
   "model": "Gemini 2.5 Flash",
   "input_per_1m_usd": 0.3,
   "output_per_1m_usd": 2.5,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00435,
   "cost_per_10k_conversations_usd": 43.5
  },
  {
   "provider": "Google",
   "model": "Gemini 2.5 Flash-Lite",
   "input_per_1m_usd": 0.1,
   "output_per_1m_usd": 0.4,
   "cached_input_per_1m_usd": null,
   "notes": "Paid tier",
   "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00119,
   "cost_per_10k_conversations_usd": 11.9
  },
  {
   "provider": "DeepSeek",
   "model": "deepseek-flash (V4.1-Flash)",
   "input_per_1m_usd": 0.3,
   "output_per_1m_usd": 1.2,
   "cached_input_per_1m_usd": 0.006,
   "notes": "Peak hours (cache miss); off-peak is half: $0.15/$0.60",
   "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00357,
   "cost_per_10k_conversations_usd": 35.7
  },
  {
   "provider": "DeepSeek",
   "model": "deepseek-v4-pro (V4-Pro)",
   "input_per_1m_usd": 1.32,
   "output_per_1m_usd": 3.96,
   "cached_input_per_1m_usd": 0.044,
   "notes": "Peak hours (cache miss); off-peak $0.66/$1.98",
   "source_url": "https://api-docs.deepseek.com/quick_start/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.014916,
   "cost_per_10k_conversations_usd": 149.16
  },
  {
   "provider": "xAI",
   "model": "grok-4.7",
   "input_per_1m_usd": 2.0,
   "output_per_1m_usd": 6.0,
   "cached_input_per_1m_usd": 0.5,
   "notes": "Prompts <200k tokens; prices double at 200k+",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0226,
   "cost_per_10k_conversations_usd": 226.0
  },
  {
   "provider": "xAI",
   "model": "grok-4.6",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 6,
   "cached_input_per_1m_usd": null,
   "notes": "Per page",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0226,
   "cost_per_10k_conversations_usd": 226.0
  },
  {
   "provider": "xAI",
   "model": "grok-4.5",
   "input_per_1m_usd": 2,
   "output_per_1m_usd": 6,
   "cached_input_per_1m_usd": null,
   "notes": "Per page",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0226,
   "cost_per_10k_conversations_usd": 226.0
  },
  {
   "provider": "xAI",
   "model": "grok-4.3",
   "input_per_1m_usd": 1.25,
   "output_per_1m_usd": 2.5,
   "cached_input_per_1m_usd": null,
   "notes": "Per page",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.013375,
   "cost_per_10k_conversations_usd": 133.75
  },
  {
   "provider": "xAI",
   "model": "grok-4.20-0309",
   "input_per_1m_usd": 1.25,
   "output_per_1m_usd": 2.5,
   "cached_input_per_1m_usd": null,
   "notes": "Reasoning and non-reasoning",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.013375,
   "cost_per_10k_conversations_usd": 133.75
  },
  {
   "provider": "xAI",
   "model": "grok-build-0.1",
   "input_per_1m_usd": 1,
   "output_per_1m_usd": 2,
   "cached_input_per_1m_usd": null,
   "notes": "Per page",
   "source_url": "https://docs.x.ai/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0107,
   "cost_per_10k_conversations_usd": 107.0
  },
  {
   "provider": "Mistral",
   "model": "Mistral Large 4",
   "input_per_1m_usd": 0.7,
   "output_per_1m_usd": 2.1,
   "cached_input_per_1m_usd": 0.07,
   "notes": "Model page; note mistral.ai/pricing FAQ states $0.5 in / $1.5 out for Mistral Large",
   "source_url": "https://docs.mistral.ai/models/mistral-large-4-0",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00791,
   "cost_per_10k_conversations_usd": 79.1
  },
  {
   "provider": "Mistral",
   "model": "Mistral Small 4",
   "input_per_1m_usd": 0.15,
   "output_per_1m_usd": 0.6,
   "cached_input_per_1m_usd": null,
   "notes": "Model page shows $0.15 /M and $0.6 /M; labels are tooltips, read as input then output",
   "source_url": "https://docs.mistral.ai/models/mistral-small-4-0-26-03",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.001785,
   "cost_per_10k_conversations_usd": 17.85
  },
  {
   "provider": "Mistral",
   "model": "Ministral 3 14B",
   "input_per_1m_usd": 0.2,
   "output_per_1m_usd": 0.2,
   "cached_input_per_1m_usd": null,
   "notes": "Model page",
   "source_url": "https://docs.mistral.ai/models/ministral-3-14b-25-12",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00202,
   "cost_per_10k_conversations_usd": 20.2
  },
  {
   "provider": "Mistral",
   "model": "Ministral 3 8B",
   "input_per_1m_usd": 0.15,
   "output_per_1m_usd": 0.15,
   "cached_input_per_1m_usd": null,
   "notes": "Model page",
   "source_url": "https://docs.mistral.ai/models/ministral-3-8b-25-12",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.001515,
   "cost_per_10k_conversations_usd": 15.15
  },
  {
   "provider": "Mistral",
   "model": "Ministral 3 3B",
   "input_per_1m_usd": 0.1,
   "output_per_1m_usd": 0.1,
   "cached_input_per_1m_usd": null,
   "notes": "Model page",
   "source_url": "https://docs.mistral.ai/models/ministral-3-3b-25-12",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00101,
   "cost_per_10k_conversations_usd": 10.1
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "llama-3.1-8b-instruct-fp8-fast",
   "input_per_1m_usd": 0.045,
   "output_per_1m_usd": 0.384,
   "cached_input_per_1m_usd": null,
   "notes": "$0.011 per 1,000 neurons; 10,000 neurons/day free",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000658,
   "cost_per_10k_conversations_usd": 6.58
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "llama-3.3-70b-instruct-fp8-fast",
   "input_per_1m_usd": 0.293,
   "output_per_1m_usd": 2.253,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.004135,
   "cost_per_10k_conversations_usd": 41.35
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "llama-4-scout-17b-16e-instruct",
   "input_per_1m_usd": 0.27,
   "output_per_1m_usd": 0.85,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.003075,
   "cost_per_10k_conversations_usd": 30.75
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "llama-3.2-1b",
   "input_per_1m_usd": 0.027,
   "output_per_1m_usd": 0.201,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000377,
   "cost_per_10k_conversations_usd": 3.77
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "gpt-oss-120b",
   "input_per_1m_usd": 0.35,
   "output_per_1m_usd": 0.75,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.003775,
   "cost_per_10k_conversations_usd": 37.75
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "gpt-oss-20b",
   "input_per_1m_usd": 0.2,
   "output_per_1m_usd": 0.3,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00208,
   "cost_per_10k_conversations_usd": 20.8
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "gemma-4-26b-a4b-it",
   "input_per_1m_usd": 0.1,
   "output_per_1m_usd": 0.3,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00113,
   "cost_per_10k_conversations_usd": 11.3
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "qwen3-30b-a3b-fp8",
   "input_per_1m_usd": 0.051,
   "output_per_1m_usd": 0.335,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000686,
   "cost_per_10k_conversations_usd": 6.86
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "glm-4.7-flash",
   "input_per_1m_usd": 0.06,
   "output_per_1m_usd": 0.4,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00081,
   "cost_per_10k_conversations_usd": 8.1
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "mistral-small-3.1-24b",
   "input_per_1m_usd": 0.351,
   "output_per_1m_usd": 0.555,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.003668,
   "cost_per_10k_conversations_usd": 36.68
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "deepseek-v4.1-flash-1017",
   "input_per_1m_usd": 0.3,
   "output_per_1m_usd": 1.2,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00357,
   "cost_per_10k_conversations_usd": 35.7
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "kimi-k2.5",
   "input_per_1m_usd": 0.6,
   "output_per_1m_usd": 3.0,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0075,
   "cost_per_10k_conversations_usd": 75.0
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "nemotron-3-120b",
   "input_per_1m_usd": 0.5,
   "output_per_1m_usd": 1.5,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00565,
   "cost_per_10k_conversations_usd": 56.5
  },
  {
   "provider": "Cloudflare Workers AI",
   "model": "granite-4.0-h-micro",
   "input_per_1m_usd": 0.017,
   "output_per_1m_usd": 0.112,
   "cached_input_per_1m_usd": null,
   "notes": "Neuron-based billing",
   "source_url": "https://developers.cloudflare.com/workers-ai/platform/pricing/",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000229,
   "cost_per_10k_conversations_usd": 2.29
  },
  {
   "provider": "Groq",
   "model": "gpt-oss-120b",
   "input_per_1m_usd": 0.15,
   "output_per_1m_usd": 0.6,
   "cached_input_per_1m_usd": null,
   "notes": "On-demand",
   "source_url": "https://console.groq.com/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.001785,
   "cost_per_10k_conversations_usd": 17.85
  },
  {
   "provider": "Groq",
   "model": "gpt-oss-20b",
   "input_per_1m_usd": 0.075,
   "output_per_1m_usd": 0.3,
   "cached_input_per_1m_usd": null,
   "notes": "On-demand",
   "source_url": "https://console.groq.com/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.000892,
   "cost_per_10k_conversations_usd": 8.92
  },
  {
   "provider": "Groq",
   "model": "qwen3.8-27b",
   "input_per_1m_usd": 0.8,
   "output_per_1m_usd": 4.0,
   "cached_input_per_1m_usd": null,
   "notes": "On-demand",
   "source_url": "https://console.groq.com/docs/models",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.01,
   "cost_per_10k_conversations_usd": 100.0
  },
  {
   "provider": "Together AI",
   "model": "gpt-oss-120B",
   "input_per_1m_usd": 0.15,
   "output_per_1m_usd": 0.6,
   "cached_input_per_1m_usd": null,
   "notes": "Serverless",
   "source_url": "https://www.together.ai/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.001785,
   "cost_per_10k_conversations_usd": 17.85
  },
  {
   "provider": "Together AI",
   "model": "DeepSeek V4.1 Flash",
   "input_per_1m_usd": 0.3,
   "output_per_1m_usd": 1.2,
   "cached_input_per_1m_usd": null,
   "notes": "Serverless",
   "source_url": "https://www.together.ai/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.00357,
   "cost_per_10k_conversations_usd": 35.7
  },
  {
   "provider": "Together AI",
   "model": "GLM-5.3",
   "input_per_1m_usd": 1.4,
   "output_per_1m_usd": 4.4,
   "cached_input_per_1m_usd": null,
   "notes": "Serverless",
   "source_url": "https://www.together.ai/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.01594,
   "cost_per_10k_conversations_usd": 159.4
  },
  {
   "provider": "Together AI",
   "model": "Kimi K3",
   "input_per_1m_usd": 3,
   "output_per_1m_usd": 15,
   "cached_input_per_1m_usd": null,
   "notes": "Serverless",
   "source_url": "https://www.together.ai/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.0375,
   "cost_per_10k_conversations_usd": 375.0
  },
  {
   "provider": "Together AI",
   "model": "Qwen3.7-Max",
   "input_per_1m_usd": 2.5,
   "output_per_1m_usd": 7.5,
   "cached_input_per_1m_usd": null,
   "notes": "Serverless",
   "source_url": "https://www.together.ai/pricing",
   "checked": "2026-11-12",
   "cost_per_conversation_usd": 0.02825,
   "cost_per_10k_conversations_usd": 282.5
  }
 ]
}
