{
  "generatedAt": "2026-10-16",
  "note": "Auto-generated from lib/pricing.js DEFAULT_PROVIDER_PRICE_TABLE. USD per 1M tokens; unpriced entries have no verified official price.",
  "providers": {
    "openai": {
      "models": {
        "gpt-6-astra": {
          "input": 10,
          "output": 50,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 1,
          "cacheWrite": 12.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 20,
            "cacheHit": 2,
            "output": 75,
            "cacheWrite": 25
          }
        },
        "gpt-5.6-sol": {
          "input": 4,
          "output": 20,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.4,
          "cacheWrite": 5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 8,
            "cacheHit": 0.8,
            "output": 30,
            "cacheWrite": 10
          }
        },
        "gpt-5.6-terra": {
          "input": 2,
          "output": 12,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "cacheHit": 0.4,
            "output": 18,
            "cacheWrite": 5
          }
        },
        "gpt-5.6-luna": {
          "input": 0.2,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.02,
          "cacheWrite": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.4,
            "cacheHit": 0.04,
            "output": 1.8,
            "cacheWrite": 0.5
          }
        },
        "gpt-5.5": {
          "input": 5,
          "output": 30,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 10,
            "cacheHit": 1,
            "output": 45
          }
        },
        "gpt-5.5-pro": {
          "input": 30,
          "output": 180,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Published direct Standard rates: short input30/output180; long input60/output270 USD/M. The pricing table labels short context<272K, but the model detail does not establish the exact equality/context counting rule. Intentionally unpriced pending clarification; no guessed boundary.",
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 60,
            "cacheHit": 60,
            "output": 270
          },
          "unpriced": true
        },
        "gpt-5.4": {
          "input": 2.5,
          "output": 15,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 5,
            "cacheHit": 0.5,
            "output": 22.5
          }
        },
        "gpt-5.4-pro": {
          "input": 30,
          "output": 180,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 60,
            "cacheHit": 60,
            "output": 270
          }
        },
        "gpt-5.4-mini": {
          "input": 0.75,
          "output": 4.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.075
        },
        "gpt-5.4-nano": {
          "input": 0.2,
          "output": 1.25,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.02
        },
        "gpt-5.3-codex": {
          "input": 1.75,
          "cachedInput": 0.175,
          "output": 14,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official grouped Standard text-token price for Codex. Extra search/tool fees excluded. No future-billing/restricted Rosalind, embeddings or moderation units inferred."
        },
        "gpt-5.3-codex-spark": {
          "input": 1.75,
          "cachedInput": 0.175,
          "output": 14,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17"
        },
        "gpt-5.2": {
          "input": 1.75,
          "output": 14,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.175
        },
        "gpt-5.2-codex": {
          "input": 1.75,
          "cachedInput": 0.175,
          "output": 14,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-07-23 起弃用"
        },
        "gpt-5.1": {
          "input": 1.25,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.125
        },
        "gpt-5.1-codex": {
          "input": 1.07,
          "cachedInput": 0.107,
          "output": 8.5,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-07-23 起弃用"
        },
        "gpt-5.1-codex-max": {
          "input": 1.25,
          "cachedInput": 0.125,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-07-23 起弃用"
        },
        "gpt-5.1-codex-mini": {
          "input": 0.25,
          "cachedInput": 0.025,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-07-23 起弃用"
        },
        "gpt-5": {
          "input": 1.25,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.125
        },
        "gpt-5-codex": {
          "input": 1.07,
          "cachedInput": 0.107,
          "output": 8.5,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-07-23 起弃用"
        },
        "gpt-5-nano": {
          "input": 0.05,
          "output": 0.4,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.005
        },
        "gpt-5-2025-08-07": {
          "input": 1.25,
          "cachedInput": 0.13,
          "output": 10,
          "billingMode": "flat",
          "notes": "2025-08 首发价;当前同名 gpt-5 已调价,历史 id 保留"
        },
        "gpt-4.1-2025-04-14": {
          "input": 2,
          "cachedInput": 0.5,
          "output": 8,
          "billingMode": "flat"
        },
        "gpt-4.1-mini-2025-04-14": {
          "input": 0.4,
          "cachedInput": 0.1,
          "output": 1.6,
          "billingMode": "flat"
        },
        "gpt-6-sol": {
          "input": 2,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "cacheHit": 0.4,
            "output": 15,
            "cacheWrite": 5
          }
        },
        "gpt-6.1-sol": {
          "input": 2,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.1,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "cacheHit": 0.2,
            "output": 15,
            "cacheWrite": 5
          }
        },
        "gpt-6-luna": {
          "input": 0.1,
          "output": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket. Entire request uses long tier only above272000 input tokens.",
          "cachedInput": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.2,
            "cacheHit": 0.02,
            "output": 0.75,
            "cacheWrite": 0.25
          }
        },
        "gpt-5.2-pro": {
          "input": 21,
          "output": 168,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-5-mini": {
          "input": 0.25,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.025
        },
        "gpt-5-pro": {
          "input": 15,
          "output": 120,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-4.1": {
          "input": 2,
          "output": 8,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.5
        },
        "gpt-4.1-mini": {
          "input": 0.4,
          "output": 1.6,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.1
        },
        "gpt-4.1-nano": {
          "input": 0.1,
          "output": 0.4,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.025
        },
        "gpt-4o": {
          "input": 2.5,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 1.25
        },
        "gpt-4o-2024-05-13": {
          "input": 5,
          "output": 15,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-4o-mini": {
          "input": 0.15,
          "output": 0.6,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.075
        },
        "o1": {
          "input": 15,
          "output": 60,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 7.5
        },
        "o1-pro": {
          "input": 150,
          "output": 600,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "o3-pro": {
          "input": 20,
          "output": 80,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "o3": {
          "input": 2,
          "output": 8,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.5
        },
        "o4-mini": {
          "input": 1.1,
          "output": 4.4,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.275
        },
        "o3-mini": {
          "input": 1.1,
          "output": 4.4,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket.",
          "cachedInput": 0.55
        },
        "gpt-4-turbo-2024-04-09": {
          "input": 10,
          "output": 30,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-4-0613": {
          "input": 30,
          "output": 60,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-3.5-turbo": {
          "input": 0.5,
          "output": 1.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-3.5-turbo-0125": {
          "input": 0.5,
          "output": 1.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-3.5-turbo-1106": {
          "input": 1,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "gpt-3.5-turbo-instruct": {
          "input": 1.5,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "davinci-002": {
          "input": 2,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "babbage-002": {
          "input": 0.4,
          "output": 0.4,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official Standard global direct OpenAI API token prices. Other processing tiers, regional/FedRAMP10% uplifts, tools and modality-specific costs excluded. A dash in the source means that cache rate is not independently available, not a free cache bucket."
        },
        "chat-latest": {
          "input": 5,
          "cachedInput": 0.5,
          "output": 30,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official grouped Standard text-token price for ChatGPT. Extra search/tool fees excluded. No future-billing/restricted Rosalind, embeddings or moderation units inferred."
        },
        "gpt-5-search-api": {
          "input": 1.25,
          "cachedInput": 0.125,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official grouped Standard text-token price for Search. Extra search/tool fees excluded. No future-billing/restricted Rosalind, embeddings or moderation units inferred."
        },
        "gpt-rosalind-research": {
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-15",
          "notes": "Standard global API token price. Trusted-access model; catalog inclusion does not grant access. Research billing begins 2026-10-05. Cache-write pricing does not apply."
        },
        "gpt-rosalind-discovery": {
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-15",
          "notes": "Standard global API token price. Trusted-access model; catalog inclusion does not grant access. Research billing begins 2026-10-05. Cache-write pricing does not apply."
        },
        "gpt-5.6-cyber": {
          "input": 12.5,
          "output": 75,
          "cachedInput": 1.25,
          "billingMode": "flat",
          "sourceUrl": "https://developers.openai.com/api/docs/pricing",
          "checkedAt": "2026-10-15",
          "cacheWrite": 15.625,
          "notes": "Standard global API token price for the restricted-access cyber model. No separate long-context rate is published."
        }
      }
    },
    "anthropic": {
      "models": {
        "claude-fable-5": {
          "input": 10,
          "cachedInput": 1,
          "cacheWrite": 12.5,
          "output": 50,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is20USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-5": {
          "input": 5,
          "cachedInput": 0.5,
          "cacheWrite": 6.25,
          "output": 25,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is10USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-4-8": {
          "input": 5,
          "cachedInput": 0.5,
          "cacheWrite": 6.25,
          "output": 25,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is10USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-4-7": {
          "input": 5,
          "cachedInput": 0.5,
          "cacheWrite": 6.25,
          "output": 25,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is10USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-4-6": {
          "input": 5,
          "cachedInput": 0.5,
          "cacheWrite": 6.25,
          "output": 25,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is10USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-4-5": {
          "input": 5,
          "cachedInput": 0.5,
          "cacheWrite": 6.25,
          "output": 25,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is10USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded."
        },
        "claude-sonnet-5": {
          "input": 2,
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "output": 10,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is4USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-sonnet-4-6": {
          "input": 3,
          "cachedInput": 0.3,
          "cacheWrite": 3.75,
          "output": 15,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is6USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-sonnet-4-5": {
          "input": 3,
          "cachedInput": 0.3,
          "cacheWrite": 3.75,
          "output": 15,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Current direct Claude Sonnet 4.5: maximum 200K context; 1M beta retired 2026-04-30 and over-limit requests fail. Standard rates for valid requests; 5-minute cache writes3.75USD/M, 1-hour writes6USD/M need TTL-specific accounting. Zen publishes a separate route with a long-context tier. Sources: https://platform.claude.com/docs/en/build-with-claude/context-windows and https://platform.claude.com/docs/en/release-notes/overview."
        },
        "claude-haiku-4-5": {
          "input": 1,
          "cachedInput": 0.1,
          "cacheWrite": 1.25,
          "output": 5,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is2USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded."
        },
        "claude-fable-5-1": {
          "input": 10,
          "cachedInput": 0.25,
          "cacheWrite": 12.5,
          "output": 50,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is20USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-opus-5-5": {
          "input": 4,
          "cachedInput": 0.2,
          "cacheWrite": 5,
          "output": 20,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is8USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Full1M context uses standard rates."
        },
        "claude-sonnet-5-5": {
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-15",
          "cacheWrite": 2.5,
          "notes": "Standard global API; 5-minute cache writes. Direct API cache-read rate differs from OpenCode Zen."
        },
        "claude-mythos-5-1": {
          "input": 10,
          "cachedInput": 0.25,
          "cacheWrite": 12.5,
          "output": 50,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is20USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Invite-only availability does not change published per-token rates. Full1M context uses standard rates."
        },
        "claude-mythos-5": {
          "input": 10,
          "cachedInput": 1,
          "cacheWrite": 12.5,
          "output": 50,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct Claude API Standard global token rates. cacheWrite is5-minute creation;1-hour creation is20USD/M and requires separate TTL usage. Other tiers, regional premiums and tool fees excluded. Invite-only availability does not change published per-token rates. Full1M context uses standard rates."
        },
        "claude-haiku-5-5": {
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "billingMode": "flat",
          "sourceUrl": "https://platform.claude.com/docs/en/about-claude/pricing",
          "checkedAt": "2026-10-15",
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 100000,
            "cacheMiss": 0.5,
            "cacheHit": 0.05,
            "cacheWrite": 0.625,
            "output": 2.5
          },
          "notes": "Standard global API; cache writes use 5-minute TTL. Prompts over 100000 tokens, including cache reads/writes, use the higher tier for the entire request. 1-hour TTL and fast/regional surcharges are excluded."
        }
      }
    },
    "google": {
      "models": {
        "gemini-3.7-flash": {
          "input": 0.75,
          "cachedInput": 0.075,
          "output": 3.75,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing?hl=en",
          "checkedAt": "2026-10-03",
          "notes": "Standard paid direct Gemini Developer API promotional prices through 2026-12-31. Starting 2027-01-01: input1.50/cacheRead0.15/output7.50 USD/M. Cache storage is0.50 USD/M token/hour now,1.00 from2027; excluded from per-request token estimate. Output includes thinking. Zen currently charges the higher1.50/0.15/7.50 route rates. Batch/Flex/Priority/free-tier/grounding excluded."
        },
        "gemini-3.6-flash": {
          "input": 0.75,
          "cachedInput": 0.075,
          "output": 3.75,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing?hl=en",
          "checkedAt": "2026-10-03",
          "notes": "Standard paid direct Gemini Developer API promotional prices through 2026-12-31. Starting 2027-01-01: input1.50/cacheRead0.15/output7.50 USD/M. Cache storage is0.50 USD/M token/hour now,1.00 from2027; excluded from per-request token estimate. Output includes thinking. Zen currently charges the higher1.50/0.15/7.50 route rates. Batch/Flex/Priority/free-tier/grounding excluded."
        },
        "gemini-3.5-flash": {
          "input": 1.5,
          "cachedInput": 0.15,
          "output": 9,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17"
        },
        "gemini-3.5-flash-lite": {
          "input": 0.3,
          "cachedInput": 0.03,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17"
        },
        "gemini-3.1-pro-preview": {
          "input": 2,
          "cachedInput": 0.2,
          "output": 12,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17",
          "notes": "≤200K 档;>200K 按 $4/$18 计"
        },
        "gemini-3.1-pro": {
          "input": 2,
          "cachedInput": 0.2,
          "output": 12,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-25",
          "notes": "≤200K 档;>200K 按 $4/$18 计"
        },
        "gemini-3-flash": {
          "input": 0.5,
          "cachedInput": 0.05,
          "output": 3,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17",
          "notes": "Preview"
        },
        "gemini-2.5-pro": {
          "input": 1.25,
          "cachedInput": 0.125,
          "output": 10,
          "billingMode": "flat",
          "notes": "≤200K 档;>200K 按 $2.5/$15 计"
        },
        "gemini-2.5-flash": {
          "input": 0.3,
          "cachedInput": 0.03,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17"
        },
        "gemini-2.5-flash-lite": {
          "input": 0.1,
          "cachedInput": 0.01,
          "output": 0.4,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-08-17"
        },
        "gemini-3.8-flash": {
          "input": 0.75,
          "cachedInput": 0.075,
          "output": 3.75,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing?hl=en",
          "checkedAt": "2026-10-03",
          "notes": "Standard paid direct Gemini Developer API promotional prices through 2026-12-31. Starting 2027-01-01: input1.50/cacheRead0.15/output7.50 USD/M. Cache storage is0.50 USD/M token/hour now,1.00 from2027; excluded from per-request token estimate. Output includes thinking. Zen currently charges the higher1.50/0.15/7.50 route rates. Batch/Flex/Priority/free-tier/grounding excluded."
        },
        "gemini-3.1-flash-lite": {
          "input": 0.25,
          "cachedInput": 0.025,
          "output": 1.5,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing?hl=en",
          "checkedAt": "2026-10-03",
          "notes": "Standard paid text/image/video input. Audio input0.50/cacheRead0.05 USD/M is a different modality; this generic token row cannot price that accurately. Cache storage1USD/M/hour and grounding excluded."
        },
        "gemini-4-argon": {
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://ai.google.dev/gemini-api/docs/pricing",
          "checkedAt": "2026-10-15",
          "notes": "Standard paid tier. Promotional USD 2/10/0.10 input/output/cache read through 2026-11-30; official announced prices from 2026-12-01 are USD 4/20/0.20. Implicit caching only. Recheck the catalog when the promotion ends; the source does not specify a timezone."
        }
      }
    },
    "moonshot": {
      "models": {
        "kimi-k3": {
          "input": 3,
          "cachedInput": 0.3,
          "output": 15,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "官方人民币价 ¥20/¥100/缓存¥2 每百万;此处为 Go 网关美元价"
        },
        "kimi-k2.7-code": {
          "input": 0.95,
          "cachedInput": 0.19,
          "output": 4,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17"
        },
        "kimi-k2.6": {
          "input": 0.95,
          "cachedInput": 0.16,
          "output": 4,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17"
        },
        "kimi-k2.5": {
          "input": 0.6,
          "cachedInput": 0.1,
          "output": 3,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-08-05 起弃用"
        }
      }
    },
    "z-ai": {
      "models": {
        "glm-5.3": {
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-5.3-flash": {
          "input": 0.15,
          "output": 0.5,
          "cachedInput": 0.03,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-5.2": {
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-5.1": {
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-5": {
          "input": 1,
          "output": 3.2,
          "cachedInput": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-5.3-flashx": {
          "input": 0.37,
          "output": 1.25,
          "cachedInput": 0.075,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.7": {
          "input": 0.6,
          "output": 2.2,
          "cachedInput": 0.11,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.7-flashx": {
          "input": 0.07,
          "output": 0.4,
          "cachedInput": 0.01,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.6": {
          "input": 0.6,
          "output": 2.2,
          "cachedInput": 0.11,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5": {
          "input": 0.6,
          "output": 2.2,
          "cachedInput": 0.11,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5-x": {
          "input": 2.2,
          "output": 8.9,
          "cachedInput": 0.45,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5-air": {
          "input": 0.2,
          "output": 1.1,
          "cachedInput": 0.03,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5-airx": {
          "input": 1.1,
          "output": 4.5,
          "cachedInput": 0.22,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4-32b-0414-128k": {
          "input": 0.1,
          "output": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.7-flash": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5-flash": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.6v": {
          "input": 0.3,
          "output": 0.9,
          "cachedInput": 0.05,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.5v": {
          "input": 0.6,
          "output": 1.8,
          "cachedInput": 0.11,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-4.6v-flash": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct ZAI USD/token prices; cached input storage is currently limited-time free, not a separately established cache-creation-token rate. Domestic CNY routes, Coding Plans and web-search/tool fees excluded."
        },
        "glm-ocr": {
          "input": 0.03,
          "output": 0.03,
          "billingMode": "flat",
          "sourceUrl": "https://docs.z.ai/guides/overview/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Official direct token pricing row. Separate Layout Parsing API can charge per page; this token entry cannot price page billing."
        }
      }
    },
    "xai": {
      "models": {
        "grok-4.6": {
          "input": 2,
          "cachedInput": 0.5,
          "output": 6,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 4,
            "cacheHit": 1,
            "output": 12
          }
        },
        "grok-4.5": {
          "input": 2,
          "cachedInput": 0.3,
          "output": 6,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 4,
            "cacheHit": 0.6,
            "output": 12
          }
        },
        "grok-4.3": {
          "input": 1.25,
          "cachedInput": 0.2,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 2.5,
            "cacheHit": 0.4,
            "output": 5
          }
        },
        "grok-build-0.1": {
          "input": 1,
          "cachedInput": 0.2,
          "output": 2,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 2,
            "cacheHit": 0.4,
            "output": 4
          }
        },
        "grok-4.7": {
          "input": 2,
          "cachedInput": 0.5,
          "output": 6,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 4,
            "cacheHit": 1,
            "output": 12
          }
        },
        "grok-4.20-multi-agent-0309": {
          "input": 1.25,
          "cachedInput": 0.2,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 2.5,
            "cacheHit": 0.4,
            "output": 5
          }
        },
        "grok-4.20-0309-reasoning": {
          "input": 1.25,
          "cachedInput": 0.2,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 2.5,
            "cacheHit": 0.4,
            "output": 5
          }
        },
        "grok-4.20-0309-non-reasoning": {
          "input": 1.25,
          "cachedInput": 0.2,
          "output": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.x.ai/developers/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard global direct API. Official pricing table states long context ≥200000 prompt tokens, entire request. aboveInputTokens199999 represents that inclusive cutoff for integer counts; differs from Zen table >200K wording. US regional1.1x and server-tool fees excluded.",
          "longContext": {
            "aboveInputTokens": 199999,
            "cacheMiss": 2.5,
            "cacheHit": 0.4,
            "output": 5
          }
        }
      }
    },
    "alibaba": {
      "models": {
        "qwen3.8-max": {
          "input": 2,
          "cachedInput": 0.25,
          "output": 6,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "缓存写入 $2.50"
        },
        "qwen3.7-max": {
          "input": 2.5,
          "cachedInput": 0.5,
          "output": 7.5,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "缓存写入 $3.125"
        },
        "qwen3.7-plus": {
          "input": 0.4,
          "cachedInput": 0.04,
          "output": 1.6,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "≤256K 档;>256K 按 $1.2/$4.8 计;缓存写入 $0.50"
        },
        "qwen3.6-plus": {
          "input": 0.5,
          "cachedInput": 0.05,
          "output": 3,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "≤256K 档;>256K 按 $2/$6 计;缓存写入 $0.625"
        },
        "qwen3.5-plus": {
          "input": 0.2,
          "cachedInput": 0.02,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "缓存写入 $0.25"
        },
        "qwen3-plus": {
          "input": 0.4,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://www.alibabacloud.com/help/en/model-studio/model-pricing"
        }
      }
    },
    "minimax": {
      "models": {
        "minimax-m3": {
          "input": 0.3,
          "cachedInput": 0.06,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17"
        },
        "minimax-m2.7": {
          "input": 0.3,
          "cachedInput": 0.06,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17"
        },
        "minimax-m2.5": {
          "input": 0.3,
          "cachedInput": 0.06,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-17",
          "notes": "2026-08-05 起弃用"
        }
      }
    },
    "tencent": {
      "models": {
        "hunyuan-a13b": {
          "input": 0.0694,
          "output": 0.2778,
          "billingMode": "flat",
          "notes": "官方价为 CNY ¥0.5/¥2 每百万 token,按默认展示汇率 7.2 折算为 USD 入账"
        },
        "hy3": {
          "input": 0.14,
          "cachedInput": 0.035,
          "output": 0.58,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "OpenCode Go 目录价;厂商归属未官宣"
        }
      }
    },
    "xiaomi": {
      "models": {
        "mimo-v2.6-pro": {
          "input": 0.435,
          "cachedInput": 0.0036,
          "output": 0.87,
          "cny": {
            "cacheHit": 0.025,
            "cacheMiss": 3,
            "output": 6
          },
          "billingMode": "flat",
          "sourceUrl": "https://mimo.mi.com/docs/zh-CN/price/pay-as-you-go",
          "checkedAt": "2026-09-28",
          "notes": "批量推理按半价"
        },
        "mimo-v2.6-flash": {
          "input": 0.14,
          "cachedInput": 0.0028,
          "output": 0.28,
          "cny": {
            "cacheHit": 0.02,
            "cacheMiss": 1,
            "output": 2
          },
          "billingMode": "flat",
          "sourceUrl": "https://mimo.mi.com/docs/zh-CN/price/pay-as-you-go",
          "checkedAt": "2026-09-28",
          "notes": "批量推理按半价"
        },
        "mimo-v2.6-pro-ultraspeed": {
          "input": 4.35,
          "cachedInput": 0.036,
          "output": 8.7,
          "cny": {
            "cacheHit": 0.25,
            "cacheMiss": 30,
            "output": 60
          },
          "billingMode": "flat",
          "sourceUrl": "https://mimo.mi.com/docs/zh-CN/price/pay-as-you-go",
          "checkedAt": "2026-09-28",
          "notes": "速度优先档;官方未提供批量推理档"
        },
        "mimo-v2.5": {
          "input": 0.14,
          "cachedInput": 0.0028,
          "output": 0.28,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "官方标注即将下线,由 mimo-v2.6-flash 接替"
        },
        "mimo-v2.5-pro": {
          "input": 0.435,
          "cachedInput": 0.003625,
          "output": 0.87,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-17",
          "notes": "官方标注即将下线,由 mimo-v2.6-pro 接替"
        }
      }
    },
    "upstage": {
      "models": {
        "solar-pro4": {
          "input": 0.3,
          "cachedInput": 0.06,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://www.upstage.ai/pricing/api"
        },
        "solar-pro3": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.6,
          "billingMode": "flat",
          "sourceUrl": "https://www.upstage.ai/pricing/api"
        }
      }
    },
    "meta": {
      "models": {
        "muse-spark-1.2": {
          "input": 1.25,
          "cachedInput": 0.15,
          "output": 4.25,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-08-25"
        }
      }
    },
    "meituan": {
      "models": {
        "longcat-2.0": {
          "input": 0.3,
          "cachedInput": 0.006,
          "output": 1.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-08-25"
        }
      }
    },
    "nvidia": {
      "models": {
        "nvidia/nemotron-3-ultra-550b-a55b": {
          "unpriced": true,
          "billingMode": "flat",
          "notes": "Official catalog does not publish token price."
        }
      }
    },
    "mistral": {
      "models": {
        "mistral-large-2512": {
          "input": 0.5,
          "cachedInput": 0.05,
          "output": 1.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-medium-3.5": {
          "input": 1.5,
          "cachedInput": 0.15,
          "output": 7.5,
          "billingMode": "flat"
        },
        "mistral-small-4.0": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.6,
          "billingMode": "flat"
        },
        "mistral-large-latest": {
          "input": 0.5,
          "cachedInput": 0.05,
          "output": 1.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-medium-3-5": {
          "input": 1.5,
          "cachedInput": 0.15,
          "output": 7.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-medium-3": {
          "input": 1.5,
          "cachedInput": 0.15,
          "output": 7.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-medium-latest": {
          "input": 1.5,
          "cachedInput": 0.15,
          "output": 7.5,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-small-2603": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.6,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "mistral-small-latest": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.6,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-14b-2512": {
          "input": 0.2,
          "cachedInput": 0.02,
          "output": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-14b-latest": {
          "input": 0.2,
          "cachedInput": 0.02,
          "output": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-8b-2512": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.15,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-8b-latest": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0.15,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-3b-2512": {
          "input": 0.1,
          "cachedInput": 0.01,
          "output": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "ministral-3b-latest": {
          "input": 0.1,
          "cachedInput": 0.01,
          "output": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "zai-glm-5-3": {
          "input": 1.4,
          "cachedInput": 0.14,
          "output": 4.4,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded. Mistral-hosted GLM cache read0.14 differs from direct ZAI0.26."
        },
        "zai-glm-5": {
          "input": 1.4,
          "cachedInput": 0.14,
          "output": 4.4,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded. Mistral-hosted GLM cache read0.14 differs from direct ZAI0.26."
        },
        "zai-glm-latest": {
          "input": 1.4,
          "cachedInput": 0.14,
          "output": 4.4,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded. Mistral-hosted GLM cache read0.14 differs from direct ZAI0.26."
        },
        "codestral-2508": {
          "input": 0.3,
          "cachedInput": 0.03,
          "output": 0.9,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "codestral-latest": {
          "input": 0.3,
          "cachedInput": 0.03,
          "output": 0.9,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded."
        },
        "codestral-embed-2505": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded. Embedding-only endpoint, no generated output token charge; output0 represents not applicable, not free generated completions."
        },
        "codestral-embed": {
          "input": 0.15,
          "cachedInput": 0.015,
          "output": 0,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-03",
          "notes": "Standard direct Mistral global token prices. Batch/Priority/regional/tool fees excluded. Embedding-only endpoint, no generated output token charge; output0 represents not applicable, not free generated completions."
        },
        "mistral-large-4": {
          "input": 0.68,
          "output": 2.09,
          "cachedInput": 0.07,
          "billingMode": "flat",
          "sourceUrl": "https://docs.mistral.ai/inference/pricing",
          "checkedAt": "2026-10-15",
          "notes": "Current published sale price: 50% off USD 1.36/4.18/0.14 input/output/cached input. Public-preview model ID from https://docs.mistral.ai/models/mistral-large-4-0 . No promotion end date is published."
        }
      }
    },
    "opencode-go": {
      "models": {
        "glm-5.3-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.15,
          "output": 0.5,
          "cachedInput": 0.03
        },
        "glm-5.3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26
        },
        "glm-5.2": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26
        },
        "kimi-k3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 3,
          "output": 15,
          "cachedInput": 0.3
        },
        "kimi-k2.7-code": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.95,
          "output": 4,
          "cachedInput": 0.19
        },
        "kimi-k2.6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.95,
          "output": 4,
          "cachedInput": 0.16
        },
        "longcat-2.0": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.006
        },
        "longcat-2.5-preview-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "mimo-v2.6-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.14,
          "output": 0.28,
          "cachedInput": 0.0028
        },
        "mimo-v2.6-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.435,
          "output": 0.87,
          "cachedInput": 0.003625
        },
        "mimo-v2.5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.14,
          "output": 0.28,
          "cachedInput": 0.0028
        },
        "mimo-v2.5-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.435,
          "output": 0.87,
          "cachedInput": 0.003625
        },
        "minimax-m3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.06
        },
        "minimax-m2.7": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.06,
          "cacheWrite": 0.375
        },
        "muse-spark-1.3-contributor": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.1,
          "output": 0.2,
          "cachedInput": 0.002
        },
        "muse-spark-1.2-contributor": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.1,
          "output": 0.2,
          "cachedInput": 0.002
        },
        "qwen3.8-max": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.25,
          "cacheWrite": 2.5
        },
        "qwen3.8-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.15,
          "output": 0.47,
          "cachedInput": 0.016,
          "cacheWrite": 0.2
        },
        "qwen3.7-plus": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.4,
          "output": 1.6,
          "cachedInput": 0.04,
          "cacheWrite": 0.5,
          "longContext": {
            "aboveInputTokens": 256000,
            "cacheMiss": 1.2,
            "output": 4.8,
            "cacheHit": 0.12,
            "cacheWrite": 1.5
          }
        },
        "deepseek-v4.1-flash": {
          "billingMode": "utc-peak",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "offPeak": {
            "cacheMiss": 0.15,
            "output": 0.6,
            "cacheHit": 0.003
          },
          "input": 0.15,
          "output": 0.6,
          "cachedInput": 0.003,
          "notes": "Go published reference-token prices; Peak 01:00–04:00 and 06:00–10:00 UTC Monday–Friday; weekends Off-Peak. Separate from direct DeepSeek and flat Zen prices. Historical effective dates and holiday treatment not verified.",
          "peak": {
            "cacheMiss": 0.3,
            "output": 1.2,
            "cacheHit": 0.006
          }
        },
        "deepseek-v4-pro": {
          "billingMode": "utc-peak",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "offPeak": {
            "cacheMiss": 0.66,
            "output": 1.98,
            "cacheHit": 0.022
          },
          "input": 0.66,
          "output": 1.98,
          "cachedInput": 0.022,
          "notes": "Go published reference-token prices; Peak 01:00–04:00 and 06:00–10:00 UTC Monday–Friday; weekends Off-Peak. Separate from direct DeepSeek and flat Zen prices. Historical effective dates and holiday treatment not verified.",
          "peak": {
            "cacheMiss": 1.32,
            "output": 3.96,
            "cacheHit": 0.044
          }
        },
        "deepseek-v4-flash": {
          "billingMode": "utc-peak",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "offPeak": {
            "cacheMiss": 0.15,
            "output": 0.6,
            "cacheHit": 0.003
          },
          "input": 0.15,
          "output": 0.6,
          "cachedInput": 0.003,
          "notes": "Go published reference-token prices; Peak 01:00–04:00 and 06:00–10:00 UTC Monday–Friday; weekends Off-Peak. Separate from direct DeepSeek and flat Zen prices. Historical effective dates and holiday treatment not verified.",
          "peak": {
            "cacheMiss": 0.3,
            "output": 1.2,
            "cacheHit": 0.006
          }
        },
        "deepseek-v4-flash-vision-exp": {
          "billingMode": "utc-peak",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "offPeak": {
            "cacheMiss": 0.15,
            "output": 0.6,
            "cacheHit": 0.003
          },
          "input": 0.15,
          "output": 0.6,
          "cachedInput": 0.003,
          "notes": "Go published reference-token prices; Peak 01:00–04:00 and 06:00–10:00 UTC Monday–Friday; weekends Off-Peak. Separate from direct DeepSeek and flat Zen prices. Historical effective dates and holiday treatment not verified.",
          "peak": {
            "cacheMiss": 0.3,
            "output": 1.2,
            "cacheHit": 0.006
          }
        },
        "hy4-preview": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.834,
          "output": 2.501,
          "cachedInput": 0.042
        },
        "hy3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.14,
          "output": 0.58,
          "cachedInput": 0.035
        },
        "space-bunny-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "grok-4.7": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 12,
            "cacheHit": 1
          }
        },
        "grok-4.6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 12,
            "cacheHit": 1
          }
        },
        "gpt-6-luna": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.2,
            "output": 0.75,
            "cacheHit": 0.02,
            "cacheWrite": 0.25
          }
        },
        "gpt-5.6-luna": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/go",
          "checkedAt": "2026-10-03",
          "input": 0.2,
          "output": 1.2,
          "cachedInput": 0.02,
          "cacheWrite": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.4,
            "output": 1.8,
            "cacheHit": 0.04,
            "cacheWrite": 0.5
          }
        },
        "step-5-preview-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/go/",
          "checkedAt": "2026-10-15"
        },
        "cat-jam-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/go/",
          "checkedAt": "2026-10-15"
        },
        "space-bunny": {
          "input": 0.15,
          "output": 0.6,
          "cachedInput": 0.03,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/go/",
          "checkedAt": "2026-10-15"
        },
        "claude-haiku-5-5": {
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 100000,
            "cacheMiss": 0.5,
            "cacheHit": 0.05,
            "output": 2.5,
            "cacheWrite": 0.625
          },
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/go/",
          "checkedAt": "2026-10-15"
        },
        "gemini-4-argon-contributor": {
          "input": 4,
          "output": 20,
          "cachedInput": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/go/",
          "checkedAt": "2026-10-15",
          "notes": "Current published promotional rate; gateway pricing is independent of the direct API."
        }
      }
    },
    "openrouter": {
      "models": {
        "meta/muse-spark-1.3-contributor": {
          "input": 0.1,
          "cachedInput": 0.002,
          "output": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://openrouter.ai/api/v1/models",
          "checkedAt": "2026-09-17"
        },
        "google/gemini-3.8-flash": {
          "input": 0.75,
          "cachedInput": 0.075,
          "cacheWrite": 0.041667,
          "output": 3.75,
          "billingMode": "flat",
          "sourceUrl": "https://openrouter.ai/api/v1/models",
          "checkedAt": "2026-09-17"
        },
        "qwen/qwen3.8-flash": {
          "input": 0.15,
          "cachedInput": 0.016,
          "cacheWrite": 0.2,
          "output": 0.47,
          "billingMode": "flat",
          "sourceUrl": "https://openrouter.ai/api/v1/models",
          "checkedAt": "2026-09-17"
        },
        "z-ai/glm-5.3-flash": {
          "input": 0.09,
          "cachedInput": 0.018,
          "output": 0.3,
          "billingMode": "flat",
          "sourceUrl": "https://openrouter.ai/api/v1/models",
          "checkedAt": "2026-09-17"
        }
      }
    },
    "opendesign": {
      "models": {
        "claude-fable-5": {
          "cacheMiss": 10,
          "output": 50,
          "cacheHit": 1,
          "cacheWrite": 12.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-fable-5.1": {
          "cacheMiss": 10,
          "output": 50,
          "cacheHit": 0.25,
          "cacheWrite": 12.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-haiku-5.5": {
          "cacheMiss": 0.1,
          "output": 0.5,
          "cacheHit": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 100000,
            "cacheMiss": 0.5,
            "output": 2.5,
            "cacheHit": 0.05,
            "cacheWrite": 0.625
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-opus-4.8": {
          "cacheMiss": 5,
          "output": 25,
          "cacheHit": 0.5,
          "cacheWrite": 6.25,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-opus-5": {
          "cacheMiss": 5,
          "output": 25,
          "cacheHit": 0.5,
          "cacheWrite": 6.25,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-opus-5.5": {
          "cacheMiss": 4,
          "output": 20,
          "cacheHit": 0.2,
          "cacheWrite": 5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-sonnet-5": {
          "cacheMiss": 2,
          "output": 10,
          "cacheHit": 0.2,
          "cacheWrite": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "claude-sonnet-5.5": {
          "cacheMiss": 2,
          "output": 10,
          "cacheHit": 0.2,
          "cacheWrite": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "deepseek-v4.1-flash": {
          "cacheMiss": 0.3,
          "output": 1.2,
          "cacheHit": 0.006,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "deepseek-v4-flash": {
          "cacheMiss": 0.44,
          "output": 1.32,
          "cacheHit": 0.014,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "deepseek-v4-flash-vision-exp": {
          "cacheMiss": 0.44,
          "output": 1.32,
          "cacheHit": 0.014,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "deepseek-v4-pro": {
          "cacheMiss": 1.32,
          "output": 3.96,
          "cacheHit": 0.044,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gemini-3.7-flash": {
          "cacheMiss": 0.75,
          "output": 3.75,
          "cacheHit": 0.075,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gemini-3.8-flash": {
          "cacheMiss": 0.75,
          "output": 3.75,
          "cacheHit": 0.075,
          "cacheWrite": 0.08333,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "glm-5.2": {
          "cacheMiss": 1.4,
          "output": 4.4,
          "cacheHit": 0.26,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "glm-5.3-flash": {
          "cacheMiss": 0.075,
          "output": 0.25,
          "cacheHit": 0.015,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "glm-5.3-flashx": {
          "cacheMiss": 0.37,
          "output": 1.25,
          "cacheHit": 0.075,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-5.6-luna": {
          "cacheMiss": 0.2,
          "output": 1.2,
          "cacheHit": 0.02,
          "cacheWrite": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.4,
            "output": 1.8,
            "cacheHit": 0.04,
            "cacheWrite": 0.5
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-5.6-sol": {
          "cacheMiss": 4,
          "output": 20,
          "cacheHit": 0.4,
          "cacheWrite": 5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 8,
            "output": 30,
            "cacheHit": 0.8,
            "cacheWrite": 10
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-5.6-terra": {
          "cacheMiss": 2,
          "output": 12,
          "cacheHit": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "output": 18,
            "cacheHit": 0.4,
            "cacheWrite": 5
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-6.1-sol": {
          "cacheMiss": 2,
          "output": 10,
          "cacheHit": 0.1,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "output": 15,
            "cacheHit": 0.2,
            "cacheWrite": 5
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-6-astra": {
          "cacheMiss": 10,
          "output": 50,
          "cacheHit": 1,
          "cacheWrite": 12.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 20,
            "output": 75,
            "cacheHit": 2,
            "cacheWrite": 25
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-6-luna": {
          "cacheMiss": 0.1,
          "output": 0.5,
          "cacheHit": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.2,
            "output": 0.75,
            "cacheHit": 0.02,
            "cacheWrite": 0.25
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "gpt-6-sol": {
          "cacheMiss": 2,
          "output": 10,
          "cacheHit": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "output": 15,
            "cacheHit": 0.4,
            "cacheWrite": 5
          },
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "grok-4.5": {
          "cacheMiss": 2,
          "output": 6,
          "cacheHit": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "grok-4.6": {
          "cacheMiss": 2,
          "output": 6,
          "cacheHit": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "grok-4.7": {
          "cacheMiss": 2,
          "output": 6,
          "cacheHit": 0.5,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "hy4-preview": {
          "cacheMiss": 0.834,
          "output": 2.501,
          "cacheHit": 0.042,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "kimi-k2.7-code": {
          "cacheMiss": 0.95,
          "output": 4,
          "cacheHit": 0.19,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "kimi-k3": {
          "cacheMiss": 3,
          "output": 15,
          "cacheHit": 0.3,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "mimo-v2.6-flash": {
          "cacheMiss": 0.14,
          "output": 0.28,
          "cacheHit": 0.0028,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "mimo-v2.6-pro": {
          "cacheMiss": 0.435,
          "output": 0.87,
          "cacheHit": 0.0036,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "muse-spark-1.3": {
          "cacheMiss": 1.25,
          "output": 4.25,
          "cacheHit": 0.15,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "muse-wonder": {
          "cacheMiss": 4,
          "output": 20,
          "cacheHit": 0.2,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        },
        "qwen3.7-max": {
          "cacheMiss": 2.5,
          "output": 7.5,
          "cacheHit": 0.5,
          "cacheWrite": 3.125,
          "billingMode": "flat",
          "sourceUrl": "https://amr-api.open-design.ai/api/v1/public/model-prices",
          "checkedAt": "2026-10-15"
        }
      }
    },
    "opencode-zen": {
      "models": {
        "big-pickle": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "space-bunny-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "longcat-2.5-preview-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "mimo-v2.6-flash-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "mimo-v2.5-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "ling-3.1-flash-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "ling-3.0-flash-fin-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "nemotron-3-ultra-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "nemotron-3.5-lightning-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "muse-spark-1.3-contributor-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0,
          "cachedInput": 0
        },
        "jev-1.13-free": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0,
          "output": 0
        },
        "jev-1.13": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.042,
          "output": 0
        },
        "minimax-m3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.06
        },
        "minimax-m2.7": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.06
        },
        "minimax-m2.5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.06
        },
        "glm-5.3-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.15,
          "output": 0.5,
          "cachedInput": 0.03
        },
        "glm-5.3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26
        },
        "glm-5.2": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26
        },
        "glm-5.1": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.4,
          "output": 4.4,
          "cachedInput": 0.26
        },
        "glm-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1,
          "output": 3.2,
          "cachedInput": 0.2
        },
        "kimi-k2.7-code": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.95,
          "output": 4,
          "cachedInput": 0.19
        },
        "kimi-k3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 3,
          "output": 15,
          "cachedInput": 0.3
        },
        "kimi-k2.6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.95,
          "output": 4,
          "cachedInput": 0.16
        },
        "kimi-k2.5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.6,
          "output": 3,
          "cachedInput": 0.1
        },
        "qwen3.8-max": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.25,
          "cacheWrite": 2.5
        },
        "qwen3.8-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.15,
          "output": 0.47,
          "cachedInput": 0.016,
          "cacheWrite": 0.2
        },
        "qwen3.7-max": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2.5,
          "output": 7.5,
          "cachedInput": 0.5,
          "cacheWrite": 3.125
        },
        "qwen3.7-plus": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.4,
          "output": 1.6,
          "cachedInput": 0.04,
          "cacheWrite": 0.5
        },
        "qwen3.6-plus": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.5,
          "output": 3,
          "cachedInput": 0.05,
          "cacheWrite": 0.625
        },
        "qwen3.5-plus": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.2,
          "output": 1.2,
          "cachedInput": 0.02,
          "cacheWrite": 0.25
        },
        "deepseek-v4.1-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 1.2,
          "cachedInput": 0.006
        },
        "deepseek-v4-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.74,
          "output": 3.48,
          "cachedInput": 0.145
        },
        "deepseek-v4-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.14,
          "output": 0.28,
          "cachedInput": 0.028
        },
        "deepseek-v4-flash-vision-exp": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.14,
          "output": 0.28,
          "cachedInput": 0.028
        },
        "claude-fable-5-1": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 10,
          "output": 50,
          "cachedInput": 0.25,
          "cacheWrite": 12.5
        },
        "claude-fable-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 10,
          "output": 50,
          "cachedInput": 1,
          "cacheWrite": 12.5
        },
        "claude-opus-5-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 4,
          "output": 20,
          "cachedInput": 0.2,
          "cacheWrite": 5
        },
        "claude-opus-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        "claude-opus-4-8": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        "claude-opus-4-7": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        "claude-opus-4-6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        "claude-opus-4-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 25,
          "cachedInput": 0.5,
          "cacheWrite": 6.25
        },
        "claude-sonnet-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 10,
          "cachedInput": 0.2,
          "cacheWrite": 2.5
        },
        "claude-sonnet-4-6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 3,
          "output": 15,
          "cachedInput": 0.3,
          "cacheWrite": 3.75
        },
        "claude-sonnet-4-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 3,
          "output": 15,
          "cachedInput": 0.3,
          "cacheWrite": 3.75,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 6,
            "output": 22.5,
            "cacheHit": 0.6,
            "cacheWrite": 7.5
          }
        },
        "claude-haiku-4-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1,
          "output": 5,
          "cachedInput": 0.1,
          "cacheWrite": 1.25
        },
        "gemini-3.8-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.5,
          "output": 7.5,
          "cachedInput": 0.15
        },
        "gemini-3.7-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.5,
          "output": 7.5,
          "cachedInput": 0.15
        },
        "gemini-3.6-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.5,
          "output": 7.5,
          "cachedInput": 0.15
        },
        "gemini-3.5-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.5,
          "output": 9,
          "cachedInput": 0.15
        },
        "gemini-3.5-flash-lite": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.3,
          "output": 2.5,
          "cachedInput": 0.03
        },
        "gemini-3.1-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 12,
          "cachedInput": 0.2,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 18,
            "cacheHit": 0.4
          }
        },
        "gemini-3-flash": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.5,
          "output": 3,
          "cachedInput": 0.05
        },
        "grok-4.7": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 12,
            "cacheHit": 1
          }
        },
        "grok-4.6": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 12,
            "cacheHit": 1
          }
        },
        "grok-4.5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 6,
          "cachedInput": 0.3,
          "longContext": {
            "aboveInputTokens": 200000,
            "cacheMiss": 4,
            "output": 12,
            "cacheHit": 0.6
          }
        },
        "grok-build-0.1": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1,
          "output": 2,
          "cachedInput": 0.2
        },
        "muse-spark-1.3": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.25,
          "output": 4.25,
          "cachedInput": 0.15
        },
        "muse-spark-1.2": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.25,
          "output": 4.25,
          "cachedInput": 0.15
        },
        "gpt-6-astra": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 10,
          "output": 50,
          "cachedInput": 1,
          "cacheWrite": 12.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 20,
            "output": 75,
            "cacheHit": 2,
            "cacheWrite": 25
          }
        },
        "gpt-6-sol": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 10,
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "output": 15,
            "cacheHit": 0.4,
            "cacheWrite": 5
          }
        },
        "gpt-6.1-sol": {
          "input": 2,
          "output": 10,
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "cacheHit": 0.4,
            "output": 15,
            "cacheWrite": 5
          },
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "gpt-6-luna": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.2,
            "output": 0.75,
            "cacheHit": 0.02,
            "cacheWrite": 0.25
          }
        },
        "gpt-5.6-sol": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 4,
          "output": 20,
          "cachedInput": 0.4,
          "cacheWrite": 5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 8,
            "output": 30,
            "cacheHit": 0.8,
            "cacheWrite": 10
          }
        },
        "gpt-5.6-terra": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2,
          "output": 12,
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 4,
            "output": 18,
            "cacheHit": 0.4,
            "cacheWrite": 5
          }
        },
        "gpt-5.6-luna": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.2,
          "output": 1.2,
          "cachedInput": 0.02,
          "cacheWrite": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 0.4,
            "output": 1.8,
            "cacheHit": 0.04,
            "cacheWrite": 0.5
          }
        },
        "gpt-5.5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 5,
          "output": 30,
          "cachedInput": 0.5,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 10,
            "output": 45,
            "cacheHit": 1
          }
        },
        "gpt-5.5-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 30,
          "output": 180,
          "cachedInput": 30
        },
        "gpt-5.4": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 2.5,
          "output": 15,
          "cachedInput": 0.25,
          "longContext": {
            "aboveInputTokens": 272000,
            "cacheMiss": 5,
            "output": 22.5,
            "cacheHit": 0.5
          }
        },
        "gpt-5.4-pro": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 30,
          "output": 180,
          "cachedInput": 30
        },
        "gpt-5.4-mini": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.75,
          "output": 4.5,
          "cachedInput": 0.075
        },
        "gpt-5.4-nano": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.2,
          "output": 1.25,
          "cachedInput": 0.02
        },
        "gpt-5.3-codex-spark": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.75,
          "output": 14,
          "cachedInput": 0.175
        },
        "gpt-5.3-codex": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.75,
          "output": 14,
          "cachedInput": 0.175
        },
        "gpt-5.2": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.75,
          "output": 14,
          "cachedInput": 0.175
        },
        "gpt-5.2-codex": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.75,
          "output": 14,
          "cachedInput": 0.175
        },
        "gpt-5.1": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.07,
          "output": 8.5,
          "cachedInput": 0.107
        },
        "gpt-5.1-codex": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.07,
          "output": 8.5,
          "cachedInput": 0.107
        },
        "gpt-5.1-codex-max": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.25,
          "output": 10,
          "cachedInput": 0.125
        },
        "gpt-5.1-codex-mini": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.25,
          "output": 2,
          "cachedInput": 0.025
        },
        "gpt-5": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.07,
          "output": 8.5,
          "cachedInput": 0.107
        },
        "gpt-5-codex": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 1.07,
          "output": 8.5,
          "cachedInput": 0.107
        },
        "gpt-5-nano": {
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/docs/zen",
          "checkedAt": "2026-10-03",
          "input": 0.05,
          "output": 0.4,
          "cachedInput": 0.005
        },
        "deepseek-v4.1-flash-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "cat-jam-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "step-5-preview-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "exo-free": {
          "input": 0,
          "output": 0,
          "cachedInput": 0,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "mistral-large-4": {
          "input": 0.68,
          "output": 2.09,
          "cachedInput": 0.07,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15",
          "notes": "Current published gateway rate; independent of the direct API."
        },
        "claude-sonnet-5-5": {
          "input": 2,
          "output": 10,
          "cachedInput": 0.2,
          "cacheWrite": 2.5,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "claude-haiku-5-5": {
          "input": 0.1,
          "output": 0.5,
          "cachedInput": 0.01,
          "cacheWrite": 0.125,
          "longContext": {
            "aboveInputTokens": 100000,
            "cacheMiss": 0.5,
            "cacheHit": 0.05,
            "output": 2.5,
            "cacheWrite": 0.625
          },
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15"
        },
        "gemini-4-argon": {
          "input": 2,
          "output": 10,
          "cachedInput": 0.1,
          "billingMode": "flat",
          "sourceUrl": "https://opencode.ai/v2/docs/console/models/",
          "checkedAt": "2026-10-15",
          "notes": "Current published promotional rate; gateway pricing is independent of the direct API."
        }
      }
    },
    "stepfun": {
      "models": {
        "step-5-preview": {
          "input": 1,
          "cachedInput": 0.1,
          "output": 2.7,
          "billingMode": "flat",
          "sourceUrl": "https://platform.stepfun.ai/docs/en/guides/pricing/details",
          "checkedAt": "2026-10-16",
          "notes": "StepFun global API, USD per million tokens. Reasoning is included in output. Regional pricing, Step Plan, search and audio/image generation charges are not included."
        },
        "step-3.7-flash": {
          "input": 0.2,
          "cachedInput": 0.04,
          "output": 1.15,
          "billingMode": "flat",
          "sourceUrl": "https://platform.stepfun.ai/docs/en/guides/pricing/details",
          "checkedAt": "2026-10-16",
          "notes": "StepFun global API, USD per million tokens. Reasoning is included in output. Regional pricing, Step Plan, search and audio/image generation charges are not included."
        },
        "step-3.5-flash": {
          "input": 0.1,
          "cachedInput": 0.02,
          "output": 0.3,
          "billingMode": "flat",
          "sourceUrl": "https://platform.stepfun.ai/docs/en/guides/pricing/details",
          "checkedAt": "2026-10-16",
          "notes": "StepFun global API, USD per million tokens. Reasoning is included in output. Regional pricing, Step Plan, search and audio/image generation charges are not included."
        },
        "step-3.5-flash-2603": {
          "input": 0.1,
          "cachedInput": 0.02,
          "output": 0.3,
          "billingMode": "flat",
          "sourceUrl": "https://platform.stepfun.ai/docs/en/guides/pricing/details",
          "checkedAt": "2026-10-16",
          "notes": "StepFun global API, USD per million tokens. Reasoning is included in output. Regional pricing, Step Plan, search and audio/image generation charges are not included."
        },
        "step-1o-turbo-vision": {
          "input": 0.36,
          "cachedInput": 0.07,
          "output": 1.15,
          "billingMode": "flat",
          "sourceUrl": "https://platform.stepfun.ai/docs/en/guides/pricing/details",
          "checkedAt": "2026-10-16",
          "notes": "StepFun global API, USD per million tokens. Reasoning is included in output. Regional pricing, Step Plan, search and audio/image generation charges are not included."
        }
      }
    }
  }
}