{
  "meta": {
    "schemaVersion": 2,
    "verifiedAt": "2026-08-02",
    "currency": "USD",
    "unit": "per_1m_tokens",
    "disclaimer": "Prices are verified against official provider documentation on the stated date. Provider invoices, negotiated rates, taxes and cloud-platform pricing may differ."
  },
  "models": [
    {
      "id": "gpt-5.6-sol",
      "slug": "gpt-5-6-sol",
      "provider": "OpenAI",
      "name": "GPT-5.6 Sol",
      "status": "active",
      "tier": "frontier",
      "description": "Frontier reasoning and coding model for complex professional work.",
      "contextWindow": 1050000,
      "maxOutputTokens": 128000,
      "longContextThreshold": 272000,
      "sourceUrl": "https://developers.openai.com/api/docs/models/gpt-5.6-sol",
      "pricingSourceUrl": "https://developers.openai.com/api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "openai",
      "regionalUplift": 0.1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-07-30",
          "modes": {
            "standard": {
              "input": 5,
              "cachedInput": 0.5,
              "cacheWrite": 6.25,
              "output": 30,
              "long": {
                "input": 10,
                "cachedInput": 1,
                "cacheWrite": 12.5,
                "output": 45
              }
            },
            "batch": {
              "input": 2.5,
              "cachedInput": 0.25,
              "cacheWrite": 3.125,
              "output": 15,
              "long": {
                "input": 5,
                "cachedInput": 0.5,
                "cacheWrite": 6.25,
                "output": 22.5
              }
            },
            "flex": {
              "input": 2.5,
              "cachedInput": 0.25,
              "cacheWrite": 3.125,
              "output": 15,
              "long": {
                "input": 5,
                "cachedInput": 0.5,
                "cacheWrite": 6.25,
                "output": 22.5
              }
            },
            "fast": {
              "input": 10,
              "cachedInput": 1,
              "cacheWrite": 12.5,
              "output": 60
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 10,
        "toolCallsPer1k": 2.5
      }
    },
    {
      "id": "gpt-5.6-terra",
      "slug": "gpt-5-6-terra",
      "provider": "OpenAI",
      "name": "GPT-5.6 Terra",
      "status": "active",
      "tier": "balanced",
      "description": "Balances intelligence and cost for production applications.",
      "contextWindow": 1050000,
      "maxOutputTokens": 128000,
      "longContextThreshold": 272000,
      "sourceUrl": "https://developers.openai.com/api/docs/models/gpt-5.6-terra",
      "pricingSourceUrl": "https://developers.openai.com/api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "openai",
      "regionalUplift": 0.1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-07-30",
          "modes": {
            "standard": {
              "input": 2,
              "cachedInput": 0.2,
              "cacheWrite": 2.5,
              "output": 12,
              "long": {
                "input": 4,
                "cachedInput": 0.4,
                "cacheWrite": 5,
                "output": 18
              }
            },
            "batch": {
              "input": 1,
              "cachedInput": 0.1,
              "cacheWrite": 1.25,
              "output": 6,
              "long": {
                "input": 2,
                "cachedInput": 0.2,
                "cacheWrite": 2.5,
                "output": 9
              }
            },
            "flex": {
              "input": 1,
              "cachedInput": 0.1,
              "cacheWrite": 1.25,
              "output": 6,
              "long": {
                "input": 2,
                "cachedInput": 0.2,
                "cacheWrite": 2.5,
                "output": 9
              }
            },
            "fast": {
              "input": 4,
              "cachedInput": 0.4,
              "cacheWrite": 5,
              "output": 24
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 10,
        "toolCallsPer1k": 2.5
      }
    },
    {
      "id": "gpt-5.6-luna",
      "slug": "gpt-5-6-luna",
      "provider": "OpenAI",
      "name": "GPT-5.6 Luna",
      "status": "active",
      "tier": "economy",
      "description": "Cost-sensitive GPT-5.6 model for high-volume workloads.",
      "contextWindow": 1050000,
      "maxOutputTokens": 128000,
      "longContextThreshold": 272000,
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "pricingSourceUrl": "https://developers.openai.com/api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "openai",
      "regionalUplift": 0.1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-07-30",
          "modes": {
            "standard": {
              "input": 0.2,
              "cachedInput": 0.02,
              "cacheWrite": 0.25,
              "output": 1.2,
              "long": {
                "input": 0.4,
                "cachedInput": 0.04,
                "cacheWrite": 0.5,
                "output": 1.8
              }
            },
            "batch": {
              "input": 0.1,
              "cachedInput": 0.01,
              "cacheWrite": 0.125,
              "output": 0.6,
              "long": {
                "input": 0.2,
                "cachedInput": 0.02,
                "cacheWrite": 0.25,
                "output": 0.9
              }
            },
            "flex": {
              "input": 0.1,
              "cachedInput": 0.01,
              "cacheWrite": 0.125,
              "output": 0.6,
              "long": {
                "input": 0.2,
                "cachedInput": 0.02,
                "cacheWrite": 0.25,
                "output": 0.9
              }
            },
            "fast": {
              "input": 0.4,
              "cachedInput": 0.04,
              "cacheWrite": 0.5,
              "output": 2.4
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 10,
        "toolCallsPer1k": 2.5
      }
    },
    {
      "id": "gpt-5.4-mini",
      "slug": "gpt-5-4-mini",
      "provider": "OpenAI",
      "name": "GPT-5.4 Mini",
      "status": "active",
      "tier": "balanced",
      "description": "Smaller reasoning model for lower-cost agent and coding tasks.",
      "contextWindow": 400000,
      "maxOutputTokens": 128000,
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "pricingSourceUrl": "https://developers.openai.com/api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "openai",
      "regionalUplift": 0.1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-03-17",
          "modes": {
            "standard": {
              "input": 0.75,
              "cachedInput": 0.075,
              "output": 4.5
            },
            "batch": {
              "input": 0.375,
              "cachedInput": 0.0375,
              "output": 2.25
            },
            "fast": {
              "input": 1.5,
              "cachedInput": 0.15,
              "output": 9
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 10,
        "toolCallsPer1k": 2.5
      }
    },
    {
      "id": "gpt-5.4-nano",
      "slug": "gpt-5-4-nano",
      "provider": "OpenAI",
      "name": "GPT-5.4 Nano",
      "status": "active",
      "tier": "economy",
      "description": "Low-cost model for classification, extraction and simple tool calls.",
      "contextWindow": 400000,
      "maxOutputTokens": 128000,
      "sourceUrl": "https://developers.openai.com/api/docs/pricing",
      "pricingSourceUrl": "https://developers.openai.com/api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "openai",
      "regionalUplift": 0.1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-03-17",
          "modes": {
            "standard": {
              "input": 0.2,
              "cachedInput": 0.02,
              "output": 1.25
            },
            "batch": {
              "input": 0.1,
              "cachedInput": 0.01,
              "output": 0.625
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 10,
        "toolCallsPer1k": 2.5
      }
    },
    {
      "id": "claude-fable-5",
      "slug": "claude-fable-5",
      "provider": "Anthropic",
      "name": "Claude Fable 5",
      "status": "active",
      "tier": "frontier",
      "description": "Highest-tier Claude model for long-running, capability-first workflows.",
      "contextWindow": 1000000,
      "maxOutputTokens": 128000,
      "sourceUrl": "https://platform.claude.com/docs/en/about-claude/models/overview",
      "pricingSourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "anthropic_new",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-01-01",
          "modes": {
            "standard": {
              "input": 10,
              "cachedInput": 1,
              "cacheWrite": 12.5,
              "cacheWrite1h": 20,
              "output": 50
            },
            "batch": {
              "input": 5,
              "output": 25
            }
          }
        }
      ]
    },
    {
      "id": "claude-opus-5",
      "slug": "claude-opus-5",
      "provider": "Anthropic",
      "name": "Claude Opus 5",
      "status": "active",
      "tier": "frontier",
      "description": "Advanced Claude model for complex agentic coding and enterprise work.",
      "contextWindow": 1000000,
      "maxOutputTokens": 128000,
      "sourceUrl": "https://platform.claude.com/docs/en/about-claude/models/overview",
      "pricingSourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "anthropic_new",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-01-01",
          "modes": {
            "standard": {
              "input": 5,
              "cachedInput": 0.5,
              "cacheWrite": 6.25,
              "cacheWrite1h": 10,
              "output": 25
            },
            "batch": {
              "input": 2.5,
              "output": 12.5
            }
          }
        }
      ]
    },
    {
      "id": "claude-sonnet-5",
      "slug": "claude-sonnet-5",
      "provider": "Anthropic",
      "name": "Claude Sonnet 5",
      "status": "active",
      "tier": "balanced",
      "description": "Production-focused Claude model with temporary introductory pricing through August 2026.",
      "contextWindow": 1000000,
      "maxOutputTokens": 128000,
      "sourceUrl": "https://platform.claude.com/docs/en/about-claude/models/overview",
      "pricingSourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "anthropic_new",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-08-01",
          "effectiveTo": "2026-08-31",
          "label": "Introductory pricing",
          "modes": {
            "standard": {
              "input": 2,
              "cachedInput": 0.2,
              "cacheWrite": 2.5,
              "cacheWrite1h": 4,
              "output": 10
            },
            "batch": {
              "input": 1,
              "output": 5
            }
          }
        },
        {
          "effectiveFrom": "2026-09-01",
          "label": "Standard pricing",
          "modes": {
            "standard": {
              "input": 3,
              "cachedInput": 0.3,
              "cacheWrite": 3.75,
              "cacheWrite1h": 6,
              "output": 15
            },
            "batch": {
              "input": 1.5,
              "output": 7.5
            }
          }
        }
      ]
    },
    {
      "id": "claude-sonnet-4.6",
      "slug": "claude-sonnet-4-6",
      "provider": "Anthropic",
      "name": "Claude Sonnet 4.6",
      "status": "active",
      "tier": "balanced",
      "description": "Stable production Claude model with prompt caching and batch support.",
      "contextWindow": 1000000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://platform.claude.com/docs/en/about-claude/models/overview",
      "pricingSourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "anthropic_legacy",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-01-01",
          "modes": {
            "standard": {
              "input": 3,
              "cachedInput": 0.3,
              "cacheWrite": 3.75,
              "cacheWrite1h": 6,
              "output": 15
            },
            "batch": {
              "input": 1.5,
              "output": 7.5
            }
          }
        }
      ]
    },
    {
      "id": "claude-haiku-4.5",
      "slug": "claude-haiku-4-5",
      "provider": "Anthropic",
      "name": "Claude Haiku 4.5",
      "status": "active",
      "tier": "economy",
      "description": "Fast Claude model for high-volume and latency-sensitive steps.",
      "contextWindow": 200000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://platform.claude.com/docs/en/about-claude/models/overview",
      "pricingSourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "anthropic_legacy",
      "pricingSchedules": [
        {
          "effectiveFrom": "2025-01-01",
          "modes": {
            "standard": {
              "input": 1,
              "cachedInput": 0.1,
              "cacheWrite": 1.25,
              "cacheWrite1h": 2,
              "output": 5
            },
            "batch": {
              "input": 0.5,
              "output": 2.5
            }
          }
        }
      ]
    },
    {
      "id": "gemini-3.6-flash",
      "slug": "gemini-3-6-flash",
      "provider": "Google",
      "name": "Gemini 3.6 Flash",
      "status": "active",
      "tier": "balanced",
      "description": "Fast multimodal Gemini model with search grounding and multiple service tiers.",
      "contextWindow": 1000000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "pricingSourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "google",
      "cacheStoragePerMTokenHour": 1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-01-01",
          "modes": {
            "standard": {
              "input": 1.5,
              "cachedInput": 0.15,
              "output": 7.5
            },
            "batch": {
              "input": 0.75,
              "cachedInput": 0.075,
              "output": 3.75
            },
            "flex": {
              "input": 0.75,
              "cachedInput": 0.075,
              "output": 3.75
            },
            "priority": {
              "input": 2.7,
              "cachedInput": 0.27,
              "output": 13.5
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 14
      }
    },
    {
      "id": "gemini-3.5-flash-lite",
      "slug": "gemini-3-5-flash-lite",
      "provider": "Google",
      "name": "Gemini 3.5 Flash-Lite",
      "status": "active",
      "tier": "economy",
      "description": "High-volume Gemini model optimized for simple agentic tasks and data processing.",
      "contextWindow": 1000000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "pricingSourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "google",
      "cacheStoragePerMTokenHour": 1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-01-01",
          "modes": {
            "standard": {
              "input": 0.3,
              "cachedInput": 0.03,
              "output": 2.5
            },
            "batch": {
              "input": 0.15,
              "cachedInput": 0.02,
              "output": 1.25
            },
            "flex": {
              "input": 0.15,
              "cachedInput": 0.02,
              "output": 1.25
            },
            "priority": {
              "input": 0.54,
              "cachedInput": 0.05,
              "output": 4.5
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 14
      }
    },
    {
      "id": "gemini-2.5-pro",
      "slug": "gemini-2-5-pro",
      "provider": "Google",
      "name": "Gemini 2.5 Pro",
      "status": "active",
      "tier": "frontier",
      "description": "Long-context Gemini reasoning model with a 200K pricing threshold.",
      "contextWindow": 1000000,
      "maxOutputTokens": 65536,
      "longContextThreshold": 200000,
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "pricingSourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "google",
      "cacheStoragePerMTokenHour": 4.5,
      "pricingSchedules": [
        {
          "effectiveFrom": "2025-01-01",
          "modes": {
            "standard": {
              "input": 1.25,
              "cachedInput": 0.125,
              "output": 10,
              "long": {
                "input": 2.5,
                "cachedInput": 0.25,
                "output": 15
              }
            },
            "batch": {
              "input": 0.625,
              "cachedInput": 0.125,
              "output": 5,
              "long": {
                "input": 1.25,
                "cachedInput": 0.25,
                "output": 7.5
              }
            },
            "flex": {
              "input": 0.625,
              "cachedInput": 0.125,
              "output": 5,
              "long": {
                "input": 1.25,
                "cachedInput": 0.25,
                "output": 7.5
              }
            },
            "priority": {
              "input": 2.25,
              "cachedInput": 0.225,
              "output": 18,
              "long": {
                "input": 4.5,
                "cachedInput": 0.45,
                "output": 27
              }
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 35
      }
    },
    {
      "id": "gemini-2.5-flash",
      "slug": "gemini-2-5-flash",
      "provider": "Google",
      "name": "Gemini 2.5 Flash",
      "status": "active",
      "tier": "economy",
      "description": "Hybrid reasoning model with one-million-token context and low standard pricing.",
      "contextWindow": 1000000,
      "maxOutputTokens": 65536,
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "pricingSourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "google",
      "cacheStoragePerMTokenHour": 1,
      "pricingSchedules": [
        {
          "effectiveFrom": "2025-01-01",
          "modes": {
            "standard": {
              "input": 0.3,
              "cachedInput": 0.03,
              "output": 2.5
            },
            "batch": {
              "input": 0.15,
              "cachedInput": 0.03,
              "output": 1.25
            },
            "flex": {
              "input": 0.15,
              "cachedInput": 0.03,
              "output": 1.25
            }
          }
        }
      ],
      "toolPricing": {
        "webSearchPer1k": 35
      }
    },
    {
      "id": "mistral-medium-3.5",
      "slug": "mistral-medium-3-5",
      "provider": "Mistral",
      "name": "Mistral Medium 3.5",
      "status": "active",
      "tier": "frontier",
      "description": "Multimodal Mistral model optimized for agentic and coding workloads.",
      "contextWindow": 256000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
      "pricingSourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-medium-3-5-26-04",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "mistral",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-04-28",
          "modes": {
            "standard": {
              "input": 1.5,
              "output": 7.5
            },
            "batch": {
              "input": 0.75,
              "output": 3.75
            }
          }
        }
      ]
    },
    {
      "id": "mistral-large-3",
      "slug": "mistral-large-3",
      "provider": "Mistral",
      "name": "Mistral Large 3",
      "status": "active",
      "tier": "balanced",
      "description": "General-purpose open-weight multimodal model with competitive token pricing.",
      "contextWindow": 256000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-large-3-25-12",
      "pricingSourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-large-3-25-12",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "mistral",
      "pricingSchedules": [
        {
          "effectiveFrom": "2025-12-02",
          "modes": {
            "standard": {
              "input": 0.5,
              "output": 1.5
            },
            "batch": {
              "input": 0.25,
              "output": 0.75
            }
          }
        }
      ]
    },
    {
      "id": "mistral-small-4",
      "slug": "mistral-small-4",
      "provider": "Mistral",
      "name": "Mistral Small 4",
      "status": "active",
      "tier": "economy",
      "description": "Efficient hybrid instruct, reasoning and coding model.",
      "contextWindow": 256000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03",
      "pricingSourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-small-4-0-26-03",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "mistral",
      "pricingSchedules": [
        {
          "effectiveFrom": "2026-03-16",
          "modes": {
            "standard": {
              "input": 0.15,
              "output": 0.6
            },
            "batch": {
              "input": 0.075,
              "output": 0.3
            }
          }
        }
      ]
    },
    {
      "id": "ministral-3-8b",
      "slug": "ministral-3-8b",
      "provider": "Mistral",
      "name": "Ministral 3 8B",
      "status": "active",
      "tier": "economy",
      "description": "Compact text-and-vision model for low-cost processing and edge-oriented workloads.",
      "contextWindow": 256000,
      "maxOutputTokens": 64000,
      "sourceUrl": "https://docs.mistral.ai/models/model-cards/ministral-3-8b-25-12",
      "pricingSourceUrl": "https://docs.mistral.ai/models/model-cards/ministral-3-8b-25-12",
      "verifiedAt": "2026-08-02",
      "tokenizerProfile": "mistral",
      "pricingSchedules": [
        {
          "effectiveFrom": "2025-12-02",
          "modes": {
            "standard": {
              "input": 0.15,
              "output": 0.15
            },
            "batch": {
              "input": 0.075,
              "output": 0.075
            }
          }
        }
      ]
    }
  ],
  "embeddingModels": [
    {
      "id": "text-embedding-3-small",
      "provider": "OpenAI",
      "name": "text-embedding-3-small",
      "price": 0.02,
      "contextWindow": 8191,
      "verifiedAt": "2026-08-02",
      "sourceUrl": "https://developers.openai.com/api/docs/models/text-embedding-3-small"
    },
    {
      "id": "text-embedding-3-large",
      "provider": "OpenAI",
      "name": "text-embedding-3-large",
      "price": 0.13,
      "contextWindow": 8191,
      "verifiedAt": "2026-08-02",
      "sourceUrl": "https://developers.openai.com/api/docs/models/text-embedding-3-large"
    },
    {
      "id": "gemini-file-search-embedding",
      "provider": "Google",
      "name": "Gemini File Search embeddings",
      "price": 0.15,
      "contextWindow": null,
      "verifiedAt": "2026-08-02",
      "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
      "note": "Price published for File Search embedding ingestion."
    },
    {
      "id": "mistral-embed",
      "provider": "Mistral",
      "name": "Mistral Embed",
      "price": 0.1,
      "contextWindow": 8000,
      "verifiedAt": "2026-08-02",
      "sourceUrl": "https://docs.mistral.ai/models/model-cards/mistral-embed-23-12"
    }
  ]
}