{
  "name": "VantaSoft LLM API Price Dataset",
  "description": "Standard (non-batch) API prices for current Claude, GPT and Gemini models, in US dollars per million tokens, copied from each vendor's official pricing page.",
  "url": "https://www.vantasoft.com/resources/llm-prices",
  "publisher": "VantaSoft",
  "license": "https://creativecommons.org/licenses/by/4.0/",
  "attribution": "Source: VantaSoft LLM API Price Dataset (https://www.vantasoft.com/resources/llm-prices), CC BY 4.0",
  "currency": "USD",
  "unit": "per million tokens",
  "checked": "2026-10-20",
  "tracking_since": "2026-10-08",
  "sources": {
    "Anthropic": "https://platform.claude.com/docs/en/about-claude/pricing",
    "OpenAI": "https://developers.openai.com/api/docs/pricing",
    "Google": "https://ai.google.dev/gemini-api/docs/pricing"
  },
  "models": [
    {
      "vendor": "Anthropic",
      "model": "Claude Fable 5.1",
      "input": 10,
      "cached_input": 0.25,
      "output": 50,
      "cache_write": 12.5,
      "cache_write_duration": "5 minutes",
      "cache_write_extended": 20,
      "cache_write_extended_duration": "1 hour",
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": null,
      "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Anthropic",
      "model": "Claude Opus 5.5",
      "input": 4,
      "cached_input": 0.2,
      "output": 20,
      "cache_write": 5,
      "cache_write_duration": "5 minutes",
      "cache_write_extended": 8,
      "cache_write_extended_duration": "1 hour",
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": null,
      "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Anthropic",
      "model": "Claude Sonnet 5.5",
      "input": 2,
      "cached_input": 0.1,
      "output": 10,
      "cache_write": 2.5,
      "cache_write_duration": "5 minutes",
      "cache_write_extended": 4,
      "cache_write_extended_duration": "1 hour",
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": null,
      "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Anthropic",
      "model": "Claude Haiku 5.5",
      "input": 0.1,
      "cached_input": 0.01,
      "output": 0.5,
      "cache_write": 0.125,
      "cache_write_duration": "5 minutes",
      "cache_write_extended": 0.2,
      "cache_write_extended_duration": "1 hour",
      "long_context_over_tokens": 100000,
      "long_context_input": 0.5,
      "long_context_cached_input": 0.05,
      "long_context_output": 2.5,
      "long_context_cache_write": 0.625,
      "long_context_cache_write_extended": 1,
      "note": null,
      "source_url": "https://platform.claude.com/docs/en/about-claude/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "OpenAI",
      "model": "GPT-6 Astra",
      "input": 10,
      "cached_input": 1,
      "output": 50,
      "cache_write": 12.5,
      "cache_write_duration": "30 minutes",
      "cache_write_extended": 25,
      "cache_write_extended_duration": "12 hours",
      "long_context_over_tokens": 272000,
      "long_context_input": 20,
      "long_context_cached_input": 2,
      "long_context_output": 75,
      "long_context_cache_write": 25,
      "long_context_cache_write_extended": 50,
      "note": null,
      "source_url": "https://developers.openai.com/api/docs/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "OpenAI",
      "model": "GPT-6.1 Sol",
      "input": 2,
      "cached_input": 0.1,
      "output": 10,
      "cache_write": 2.5,
      "cache_write_duration": "30 minutes",
      "cache_write_extended": 5,
      "cache_write_extended_duration": "12 hours",
      "long_context_over_tokens": 272000,
      "long_context_input": 4,
      "long_context_cached_input": 0.2,
      "long_context_output": 15,
      "long_context_cache_write": 5,
      "long_context_cache_write_extended": 10,
      "note": null,
      "source_url": "https://developers.openai.com/api/docs/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "OpenAI",
      "model": "GPT-6 Luna",
      "input": 0.1,
      "cached_input": 0.01,
      "output": 0.5,
      "cache_write": 0.125,
      "cache_write_duration": "30 minutes",
      "cache_write_extended": 0.25,
      "cache_write_extended_duration": "12 hours",
      "long_context_over_tokens": 272000,
      "long_context_input": 0.2,
      "long_context_cached_input": 0.02,
      "long_context_output": 0.75,
      "long_context_cache_write": 0.25,
      "long_context_cache_write_extended": 0.5,
      "note": null,
      "source_url": "https://developers.openai.com/api/docs/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Google",
      "model": "Gemini 4 Argon",
      "input": 2,
      "cached_input": 0.1,
      "output": 10,
      "cache_write": null,
      "cache_write_duration": null,
      "cache_write_extended": null,
      "cache_write_extended_duration": null,
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": "Introductory price through November 30, 2026. From December 1, 2026: $4.00 input, $0.20 cached input, $20.00 output.",
      "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Google",
      "model": "Gemini 3.8 Flash",
      "input": 0.75,
      "cached_input": 0.075,
      "output": 3.75,
      "cache_write": null,
      "cache_write_duration": null,
      "cache_write_extended": null,
      "cache_write_extended_duration": null,
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": "Introductory price through December 31, 2026. From January 1, 2027: $1.50 input, $0.15 cached input, $7.50 output.",
      "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
      "checked": "2026-10-20"
    },
    {
      "vendor": "Google",
      "model": "Gemini 3.5 Flash-Lite",
      "input": 0.3,
      "cached_input": 0.03,
      "output": 2.5,
      "cache_write": null,
      "cache_write_duration": null,
      "cache_write_extended": null,
      "cache_write_extended_duration": null,
      "long_context_over_tokens": null,
      "long_context_input": null,
      "long_context_cached_input": null,
      "long_context_output": null,
      "long_context_cache_write": null,
      "long_context_cache_write_extended": null,
      "note": null,
      "source_url": "https://ai.google.dev/gemini-api/docs/pricing",
      "checked": "2026-10-20"
    }
  ],
  "changes": [
    {
      "date": "2026-10-20",
      "vendor": "Google",
      "model": "Gemini 4 Argon",
      "change": "added",
      "field": null,
      "from": null,
      "to": null,
      "note": "Google's new flagship model replaces Gemini 3.1 Pro Preview as its top model in this table, at an introductory $2.00 input and $10.00 output through November 30, 2026, then $4.00 and $20.00."
    },
    {
      "date": "2026-10-20",
      "vendor": "Google",
      "model": "Gemini 3.1 Pro Preview",
      "change": "removed",
      "field": null,
      "from": null,
      "to": null,
      "note": "Replaced by Gemini 4 Argon as Google's top model. Google still lists it at $2.00 input and $12.00 output, or $4.00 and $18.00 for prompts over 200,000 tokens."
    },
    {
      "date": "2026-10-20",
      "vendor": "OpenAI",
      "model": "GPT-6 Astra",
      "change": "new_rate",
      "field": "cache_write_extended",
      "from": null,
      "to": 25,
      "note": "OpenAI now lists a 12-hour cache write next to the 30-minute one: $25.00, against $12.50 for 30 minutes. Our October 8 check found one cache-write rate."
    },
    {
      "date": "2026-10-20",
      "vendor": "OpenAI",
      "model": "GPT-6.1 Sol",
      "change": "new_rate",
      "field": "cache_write_extended",
      "from": null,
      "to": 5,
      "note": "12-hour cache write listed at $5.00, against $2.50 for 30 minutes."
    },
    {
      "date": "2026-10-20",
      "vendor": "OpenAI",
      "model": "GPT-6 Luna",
      "change": "new_rate",
      "field": "cache_write_extended",
      "from": null,
      "to": 0.25,
      "note": "12-hour cache write listed at $0.25, against $0.125 for 30 minutes."
    }
  ]
}