{
  "about": "List prices for LLM APIs in US dollars per million tokens, copied by hand from each provider's official pricing page. Standard (global) endpoints, no batch or volume discount.",
  "license": "CC BY 4.0, Mode VC (https://modevc.com/tools/)",
  "providers": {
    "anthropic": {
      "source": "https://platform.claude.com/docs/en/about-claude/pricing",
      "checked": "2026-10-29",
      "notes": "Cache read is 0.1x input (0.025x on Fable 5.1). Claude 4.7 and later use a tokenizer that makes about 30% more tokens for the same text; Sonnet 4.6 and earlier use the previous tokenizer (legacy[].tokenizer old/new). inference_geo us adds 1.1x. Batch API is 50% off.",
      "models": [
        {
          "id": "claude-fable-5-1",
          "name": "Claude Fable 5.1",
          "input": 10,
          "output": 50,
          "cacheWrite5m": 12.5,
          "cacheWrite1h": 20,
          "cacheRead": 0.25,
          "context": 1000000
        },
        {
          "id": "claude-opus-5-5",
          "name": "Claude Opus 5.5",
          "input": 4,
          "output": 20,
          "cacheWrite5m": 5,
          "cacheWrite1h": 8,
          "cacheRead": 0.2,
          "context": 1000000
        },
        {
          "id": "claude-sonnet-5-5",
          "name": "Claude Sonnet 5.5",
          "input": 2,
          "output": 10,
          "cacheWrite5m": 2.5,
          "cacheWrite1h": 4,
          "cacheRead": 0.1,
          "context": 1000000
        },
        {
          "id": "claude-haiku-5-5",
          "name": "Claude Haiku 5.5",
          "input": 0.1,
          "output": 0.5,
          "cacheWrite5m": 0.125,
          "cacheWrite1h": 0.2,
          "cacheRead": 0.01,
          "context": 1000000,
          "longPrompt": {
            "over": 100000,
            "input": 0.5,
            "output": 2.5,
            "cacheWrite5m": 0.625,
            "cacheWrite1h": 1,
            "cacheRead": 0.05
          }
        }
      ],
      "plans": {
        "source": "https://claude.com/pricing",
        "checked": "2026-10-29",
        "items": [
          {
            "name": "Pro",
            "monthly": 20,
            "annualMonthly": 17,
            "includesClaudeCode": true
          },
          {
            "name": "Max 5x",
            "monthly": 100,
            "includesClaudeCode": true,
            "apiCreditsMonthly": 100
          },
          {
            "name": "Max 20x",
            "monthly": 200,
            "includesClaudeCode": true,
            "apiCreditsMonthly": 200
          },
          {
            "name": "Enterprise",
            "seatMonthly": 20,
            "plusUsageAtApiRates": true
          }
        ],
        "notes": "Plan usage limits reset on a rolling 5-hour window plus weekly limits; Anthropic publishes no fixed token count per plan."
      },
      "batch": {
        "multiplier": 0.5,
        "note": "Batch API: 50% off input and output tokens."
      },
      "legacy": [
        {
          "id": "claude-fable-5",
          "name": "Claude Fable 5",
          "input": 10,
          "output": 50,
          "cacheWrite5m": 12.5,
          "cacheWrite1h": 20,
          "cacheRead": 1,
          "tokenizer": "new"
        },
        {
          "id": "claude-opus-5",
          "name": "Claude Opus 5",
          "input": 5,
          "output": 25,
          "cacheWrite5m": 6.25,
          "cacheWrite1h": 10,
          "cacheRead": 0.5,
          "tokenizer": "new"
        },
        {
          "id": "claude-opus-4-8",
          "name": "Claude Opus 4.8",
          "input": 5,
          "output": 25,
          "cacheWrite5m": 6.25,
          "cacheWrite1h": 10,
          "cacheRead": 0.5,
          "tokenizer": "new"
        },
        {
          "id": "claude-opus-4-7",
          "name": "Claude Opus 4.7",
          "input": 5,
          "output": 25,
          "cacheWrite5m": 6.25,
          "cacheWrite1h": 10,
          "cacheRead": 0.5,
          "tokenizer": "new"
        },
        {
          "id": "claude-opus-4-6",
          "name": "Claude Opus 4.6",
          "input": 5,
          "output": 25,
          "cacheWrite5m": 6.25,
          "cacheWrite1h": 10,
          "cacheRead": 0.5,
          "tokenizer": "old"
        },
        {
          "id": "claude-sonnet-5",
          "name": "Claude Sonnet 5",
          "input": 2,
          "output": 10,
          "cacheWrite5m": 2.5,
          "cacheWrite1h": 4,
          "cacheRead": 0.2,
          "tokenizer": "new"
        },
        {
          "id": "claude-sonnet-4-6",
          "name": "Claude Sonnet 4.6",
          "input": 3,
          "output": 15,
          "cacheWrite5m": 3.75,
          "cacheWrite1h": 6,
          "cacheRead": 0.3,
          "tokenizer": "old"
        },
        {
          "id": "claude-sonnet-4-5",
          "name": "Claude Sonnet 4.5",
          "input": 3,
          "output": 15,
          "cacheWrite5m": 3.75,
          "cacheWrite1h": 6,
          "cacheRead": 0.3,
          "tokenizer": "old"
        },
        {
          "id": "claude-haiku-4-5",
          "name": "Claude Haiku 4.5",
          "input": 1,
          "output": 5,
          "cacheWrite5m": 1.25,
          "cacheWrite1h": 2,
          "cacheRead": 0.1,
          "tokenizer": "old"
        }
      ]
    },
    "openai": {
      "source": "https://developers.openai.com/api/docs/pricing",
      "checked": "2026-10-29",
      "notes": "Standard tier, short context. Cache writes: 30-minute and 12-hour. Data residency endpoints add 10% for models released on or after 2026-03-05. GPT-5.6 Sol price is promotional through at least 2026-11-21.",
      "models": [
        {
          "id": "gpt-6-astra",
          "name": "GPT-6 Astra",
          "input": 10,
          "output": 50,
          "cacheRead": 1,
          "cacheWrite30m": 12.5,
          "cacheWrite12h": 25
        },
        {
          "id": "gpt-6.1-sol",
          "name": "GPT-6.1 Sol",
          "input": 2,
          "output": 10,
          "cacheRead": 0.1,
          "cacheWrite30m": 2.5,
          "cacheWrite12h": 5
        },
        {
          "id": "gpt-6.1-terra",
          "name": "GPT-6.1 Terra",
          "input": 1,
          "output": 5,
          "cacheRead": 0.05,
          "cacheWrite30m": 1.25,
          "cacheWrite12h": 2.5
        },
        {
          "id": "gpt-6-luna",
          "name": "GPT-6 Luna",
          "input": 0.1,
          "output": 0.5,
          "cacheRead": 0.01,
          "cacheWrite30m": 0.125,
          "cacheWrite12h": 0.25
        },
        {
          "id": "gpt-5.6-sol",
          "name": "GPT-5.6 Sol",
          "input": 4,
          "output": 20,
          "cacheRead": 0.4,
          "cacheWrite30m": 5,
          "cacheWrite12h": 10,
          "promo": true
        },
        {
          "id": "gpt-5.3-codex",
          "name": "GPT-5.3 Codex",
          "input": 1.75,
          "output": 14,
          "cacheRead": 0.175
        },
        {
          "id": "chat-latest",
          "name": "ChatGPT chat-latest",
          "input": 5,
          "output": 30,
          "cacheRead": 0.5
        }
      ],
      "tiers": {
        "batch": 0.5,
        "flex": 0.5,
        "fast": 2,
        "ultrafast": 6,
        "ultrafastModels": [
          "gpt-6-astra",
          "gpt-6.1-sol"
        ],
        "regionalUplift": 1.1,
        "note": "Flex/Batch is half the Standard price, Fast 2x, Ultrafast 6x (Astra and 6.1 Sol only). Regional data residency endpoints add 10% for models released on or after March 5, 2026. Prices are the short-context tier."
      }
    },
    "google": {
      "source": "https://ai.google.dev/gemini-api/docs/pricing",
      "checked": "2026-10-29",
      "notes": "Gemini Developer API, Standard tier, paid. Several models have dated price rises (priceChanges). Output includes thinking tokens. Gemini 3.6 Flash and 3.5 Flash-Lite are not listed yet: their tables need a manual check.",
      "models": [
        {
          "id": "gemini-4-argon",
          "name": "Gemini 4 Argon",
          "input": 2,
          "output": 10,
          "cacheRead": 0.1,
          "priceChanges": [
            {
              "from": "2026-12-01",
              "input": 4,
              "output": 20,
              "cacheRead": 0.2
            }
          ]
        },
        {
          "id": "gemini-3.8-flash",
          "name": "Gemini 3.8 Flash",
          "input": 0.75,
          "output": 3.75,
          "cacheRead": 0.075,
          "freeTier": true,
          "priceChanges": [
            {
              "from": "2027-01-01",
              "input": 1.5,
              "output": 7.5,
              "cacheRead": 0.15
            }
          ]
        },
        {
          "id": "gemini-3.1-pro-preview",
          "name": "Gemini 3.1 Pro Preview",
          "input": 2,
          "output": 12,
          "cacheRead": 0.2,
          "longPrompt": {
            "over": 200000,
            "input": 4,
            "output": 18,
            "cacheRead": 0.4
          }
        }
      ]
    },
    "deepseek": {
      "source": "https://api-docs.deepseek.com/quick_start/pricing",
      "checked": "2026-10-29",
      "notes": "Peak hours are 01:00-04:00 and 06:00-10:00 UTC, Monday to Friday, excluding Chinese public holidays; every other hour is off-peak at half the peak price. input/output/cacheRead below are peak prices. deepseek-flash is served by DeepSeek-V4.1-Flash-1017.",
      "peakHoursUtc": [
        [
          1,
          4
        ],
        [
          6,
          10
        ]
      ],
      "offPeakMultiplier": 0.5,
      "models": [
        {
          "id": "deepseek-flash",
          "name": "DeepSeek V4.1 Flash",
          "input": 0.3,
          "output": 1.2,
          "cacheRead": 0.006,
          "context": 1000000,
          "offPeak": {
            "input": 0.15,
            "output": 0.6,
            "cacheRead": 0.003
          }
        },
        {
          "id": "deepseek-v4-pro",
          "name": "DeepSeek V4 Pro",
          "input": 1.32,
          "output": 3.96,
          "cacheRead": 0.044,
          "context": 1000000,
          "offPeak": {
            "input": 0.66,
            "output": 1.98,
            "cacheRead": 0.022
          }
        }
      ],
      "tools": {
        "searchPer1k": 0.75,
        "fetchPer1k": 0.75,
        "note": "Search and Fetch API, per 1,000 successful requests. Calls made through Claude Code, Codex or DeepSeek Harness are free until 2026-11-01 00:00 Beijing time."
      }
    },
    "xai": {
      "source": "https://docs.x.ai/developers/pricing",
      "checked": "2026-10-29",
      "notes": "Docs are now branded SpaceXSI. Long-context rates apply to every token of a request once its prompt reaches 200k tokens. US regional endpoint is 1.1x. Batch API is 20% off on the models listed. Priority processing is 2x.",
      "batch": {
        "multiplier": 0.8
      },
      "usEndpoint": 1.1,
      "priority": 2,
      "models": [
        {
          "id": "grok-4.7",
          "name": "Grok 4.7",
          "input": 2,
          "output": 6,
          "cacheRead": 0.5,
          "context": 500000,
          "longPrompt": {
            "over": 200000,
            "input": 4,
            "output": 12,
            "cacheRead": 1
          }
        },
        {
          "id": "grok-4.6",
          "name": "Grok 4.6",
          "input": 2,
          "output": 6,
          "cacheRead": 0.5,
          "context": 500000,
          "longPrompt": {
            "over": 200000,
            "input": 4,
            "output": 12,
            "cacheRead": 1
          }
        },
        {
          "id": "grok-4.5",
          "name": "Grok 4.5",
          "input": 2,
          "output": 6,
          "cacheRead": 0.3,
          "context": 500000,
          "longPrompt": {
            "over": 200000,
            "input": 4,
            "output": 12,
            "cacheRead": 0.6
          }
        },
        {
          "id": "grok-4.3",
          "name": "Grok 4.3",
          "input": 1.25,
          "output": 2.5,
          "cacheRead": 0.2,
          "context": 1000000,
          "longPrompt": {
            "over": 200000,
            "input": 2.5,
            "output": 5,
            "cacheRead": 0.4
          }
        },
        {
          "id": "grok-build-0.1",
          "name": "Grok Build 0.1",
          "input": 1,
          "output": 2,
          "cacheRead": 0.2,
          "context": 256000,
          "longPrompt": {
            "over": 200000,
            "input": 2,
            "output": 4,
            "cacheRead": 0.4
          }
        }
      ],
      "tools": {
        "webSearchPer1k": 5,
        "codeExecutionPer1k": 5,
        "collectionsSearchPer1k": 2.5
      }
    }
  }
}