{
  "checked": "2026-11-15",
  "unit": "USD per million tokens",
  "note": "The providers' own list prices for standard pay-as-you-go API use. Cliff adds nothing on top: with your own key you pay the provider directly. Prices change; the source links are the final word.",
  "providers": [
    {
      "id": "anthropic",
      "name": "Anthropic",
      "env": "ANTHROPIC_API_KEY",
      "source": "https://platform.claude.com/docs/en/about-claude/pricing",
      "models": [
        {
          "id": "claude-fable-5-2",
          "name": "Claude Fable 5.2",
          "input": 8,
          "output": 40,
          "cachedInput": 0.2,
          "cacheWrite": 10
        },
        {
          "id": "claude-opus-5-5",
          "name": "Claude Opus 5.5",
          "input": 4,
          "output": 20,
          "cachedInput": 0.2,
          "default": true,
          "cacheWrite": 5
        },
        {
          "id": "claude-sonnet-5-5",
          "name": "Claude Sonnet 5.5",
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "cacheWrite": 2.5
        },
        {
          "id": "claude-haiku-5-5",
          "name": "Claude Haiku 5.5",
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "note": "Prompts over 100,000 tokens: $0.50 in, $2.50 out.",
          "cacheWrite": 0.125,
          "long": {
            "over": 100000,
            "input": 0.5,
            "output": 2.5,
            "cachedInput": 0.05,
            "cacheWrite": 0.625
          }
        },
        {
          "id": "claude-opus-5",
          "name": "Claude Opus 5",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        {
          "id": "claude-sonnet-5",
          "name": "Claude Sonnet 5",
          "input": 2,
          "output": 10,
          "cachedInput": 0.2,
          "cacheWrite": 2.5
        },
        {
          "id": "claude-haiku-4-5",
          "name": "Claude Haiku 4.5",
          "input": 1,
          "output": 5,
          "cachedInput": 0.1,
          "cacheWrite": 1.25
        }
      ],
      "tier": "Standard API, global routing; cache writes are the 5-minute price"
    },
    {
      "id": "openai",
      "name": "OpenAI",
      "env": "OPENAI_API_KEY",
      "source": "https://developers.openai.com/api/docs/pricing",
      "tier": "Standard tier, short context",
      "models": [
        {
          "id": "gpt-6-astra",
          "name": "GPT-6 Astra",
          "input": 10,
          "output": 50,
          "cachedInput": 1
        },
        {
          "id": "gpt-6.1-sol",
          "name": "GPT-6.1 Sol",
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "default": true
        },
        {
          "id": "gpt-6.1-terra",
          "name": "GPT-6.1 Terra",
          "input": 1,
          "output": 5,
          "cachedInput": 0.05
        },
        {
          "id": "gpt-6-luna",
          "name": "GPT-6 Luna",
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01
        }
      ]
    },
    {
      "id": "gemini",
      "name": "Google Gemini",
      "env": "GEMINI_API_KEY",
      "source": "https://ai.google.dev/gemini-api/docs/pricing",
      "tier": "Paid tier, standard",
      "models": [
        {
          "id": "gemini-4-carbon",
          "name": "Gemini 4 Carbon",
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "next": {
            "from": "2026-12-01",
            "input": 4,
            "output": 20,
            "cachedInput": 0.2
          }
        },
        {
          "id": "gemini-4-argon",
          "name": "Gemini 4 Argon",
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "next": {
            "from": "2026-12-01",
            "input": 4,
            "output": 20,
            "cachedInput": 0.2
          }
        },
        {
          "id": "gemini-4-hydrogen",
          "name": "Gemini 4 Hydrogen",
          "input": 1.5,
          "output": 7.5,
          "cachedInput": 0.075
        },
        {
          "id": "gemini-3.8-flash",
          "name": "Gemini 3.8 Flash",
          "input": 0.75,
          "output": 3.75,
          "cachedInput": 0.075,
          "default": true,
          "next": {
            "from": "2027-01-01",
            "input": 1.5,
            "output": 7.5,
            "cachedInput": 0.15
          }
        },
        {
          "id": "gemini-3.6-flash",
          "name": "Gemini 3.6 Flash",
          "input": 0.75,
          "output": 3.75,
          "cachedInput": 0.075,
          "next": {
            "from": "2027-01-01",
            "input": 1.5,
            "output": 7.5,
            "cachedInput": 0.15
          }
        },
        {
          "id": "gemini-3.5-flash-lite",
          "name": "Gemini 3.5 Flash-Lite",
          "input": 0.3,
          "output": 2.5,
          "cachedInput": 0.03
        },
        {
          "id": "gemini-3.1-flash-lite",
          "name": "Gemini 3.1 Flash-Lite",
          "input": 0.25,
          "output": 1.5,
          "cachedInput": 0.025
        }
      ]
    },
    {
      "id": "compatible",
      "name": "Any OpenAI-compatible endpoint",
      "env": "CLIFF_API_KEY",
      "note": "OpenRouter, Ollama, LM Studio, vLLM, llama.cpp, Groq and others. You pay whatever that endpoint charges; a model on your own computer costs nothing per token.",
      "models": []
    }
  ]
}
