{
 "schema": 1,
 "source": "models.dev catalog as cached by OpenCode",
 "retrieved": "2026-11-01",
 "notes": [
  "Costs on the site are list price at the standard tier and base context band: uncached input + cache reads + cache writes + output (reasoning included in output).",
  "Claude Code writes 1-hour cache entries (cache_write_1h); other harnesses report no cache writes unless listed.",
  "Fast/priority tiers multiply the whole bill (tiers.priority / tiers.fast).",
  "Plans (e.g. the Z.ai coding plan) bill $0; the list price is still used for comparison."
 ],
 "models": [
  {
   "model": "claude-opus-5.5",
   "catalog": "anthropic/claude-opus-5-5",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 4,
   "output": 20,
   "cache_read": 0.2,
   "cache_write_5m": 5,
   "cache_write_1h": 8,
   "reasoning_note": "reasoning tokens are billed as output",
   "region_multiplier": {
    "us": 1.1
   },
   "tiers": {
    "fast": 2
   }
  },
  {
   "model": "claude-fable-5.1",
   "catalog": "anthropic/claude-fable-5-1",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 10,
   "output": 50,
   "cache_read": 0.25,
   "cache_write_5m": 12.5,
   "cache_write_1h": 20,
   "reasoning_note": "reasoning tokens are billed as output",
   "source_note": "Anthropic list price (input, output, cache read). Cache writes use the standard 1.25x (5m) and 2x (1h) input multipliers; not yet in the models.dev cache.",
   "tiers": {}
  },
  {
   "model": "claude-haiku-5.5",
   "catalog": "anthropic/claude-haiku-5-5",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0.1,
   "output": 0.5,
   "cache_read": 0.01,
   "cache_write_5m": 0.125,
   "cache_write_1h": 0.2,
   "long_context": {
    "when": {
     "context": {
      "gt": 100000
     }
    },
    "input": 0.5,
    "output": 2.5,
    "cache_read": 0.05,
    "cache_write_5m": 0.625,
    "cache_write_1h": 1.0
   },
   "reasoning_note": "reasoning tokens are billed as output",
   "source_note": "Anthropic list price: $0.10/$0.50 for prompts up to 100K tokens, $0.50/$2.50 beyond. Cache reads 0.1x and writes 1.25x (5m) / 2x (1h) of input in each band. Claude Code requests are priced one by one in their band.",
   "tiers": {}
  },
  {
   "model": "gpt-6.1-sol",
   "catalog": "openai/gpt-6.1-sol",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 2,
   "output": 10,
   "cache_read": 0.1,
   "cache_write": 2.5,
   "reasoning_note": "reasoning tokens are billed as output",
   "long_context": {
    "when": {
     "context": {
      "gt": 272000
     }
    },
    "input": 4,
    "cache_read": 0.2,
    "cache_write": 5,
    "output": 15
   },
   "tiers": {
    "priority": 2,
    "ultrafast": 6,
    "flex": 0.5
   }
  },
  {
   "model": "gpt-6.1-terra",
   "catalog": "openai/gpt-6.1-terra",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 1,
   "output": 5,
   "cache_read": 0.05,
   "cache_write": 1.25,
   "reasoning_note": "reasoning tokens are billed as output",
   "long_context": {
    "when": {
     "context": {
      "gt": 272000
     }
    },
    "input": 2,
    "cache_read": 0.1,
    "cache_write": 2.5,
    "output": 7.5
   },
   "tiers": {
    "priority": 2,
    "flex": 0.5
   }
  },
  {
   "model": "gpt-6-astra",
   "catalog": "openai/gpt-6-astra",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 10,
   "output": 50,
   "cache_read": 1,
   "cache_write": 12.5,
   "reasoning_note": "reasoning tokens are billed as output",
   "long_context": {
    "when": {
     "context": {
      "gt": 272000
     }
    },
    "input": 20,
    "cache_read": 2,
    "cache_write": 25,
    "output": 75
   },
   "tiers": {
    "priority": 2,
    "ultrafast": 6,
    "flex": 0.5
   }
  },
  {
   "model": "deepseek-v4.1-flash",
   "catalog": "deepseek/deepseek-flash",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0.15,
   "output": 0.6,
   "cache_read": 0.003,
   "reasoning": 0.6,
   "reasoning_note": "reasoning tokens are billed as output",
   "peak_multiplier": {
    "factor": 2,
    "when": "CN weekday peak hours (UTC 01-04, 06-10, Mon-Fri, not CN holidays)"
   }
  },
  {
   "model": "glm-5.3-flash",
   "catalog": "zai/glm-5.3-flash",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0.15,
   "output": 0.5,
   "cache_read": 0.03,
   "cache_write": 0,
   "reasoning_note": "reasoning tokens are billed as output"
  },
  {
   "model": "mimo-v2.6-pro",
   "catalog": "opencode-go/mimo-v2.6-pro",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0.435,
   "output": 0.87,
   "cache_read": 0.003625,
   "reasoning_note": "reasoning tokens are billed as output"
  },
  {
   "model": "qwen3.8-flash",
   "catalog": "opencode-go/qwen3.8-flash",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0.15,
   "output": 0.47,
   "cache_read": 0.016,
   "cache_write": 0.2,
   "reasoning_note": "reasoning tokens are billed as output"
  },
  {
   "model": "grok-4.7",
   "catalog": "opencode-go/grok-4.7",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 2,
   "output": 6,
   "cache_read": 0.5,
   "reasoning_note": "reasoning tokens are billed as output",
   "long_context": {
    "when": {
     "context": {
      "gt": 200000
     }
    },
    "input": 4,
    "cache_read": 1,
    "cache_write": null,
    "output": 12
   }
  },
  {
   "model": "muse-wonder-full",
   "catalog": null,
   "currency": "USD",
   "unit": "per million tokens",
   "input": 4,
   "output": 20,
   "cache_read": 0.2,
   "cache_write": 0,
   "reasoning_note": "reasoning tokens are billed as output",
   "price_basis": "proxy",
   "plan": "Muse Code subscription (Power $50/month, Maximum $200/month); runs bill $0 per token",
   "source_note": "Muse Wonder Full has no per-token API price (subscription only, 2026-11-01). Costs use the Muse Wonder 1.0 API rate ($4 input, $0.20 cached input, $20 output per million tokens) as a proxy, so they can be compared; the real per-token price of Full is likely higher.",
   "tiers": {}
  },
  {
   "model": "gemini-4-argon",
   "catalog": "gemini-4-argon",
   "currency": "USD",
   "unit": "per million tokens",
   "input": 2,
   "output": 10,
   "cache_read": 0.1,
   "reasoning_note": "thinking tokens are billed as output",
   "note": "Gemini API standard tier introductory price through 2026-11-30 (then $4 / $20 / $0.20); third-party summaries of Google's pricing page, retrieved 2026-11-02"
  },
  {
   "model": "qwopus3.8-27b-flash-v2",
   "catalog": null,
   "currency": "USD",
   "unit": "per million tokens",
   "input": 0,
   "output": 0,
   "cache_read": 0,
   "note": "Runs locally on the owner's hardware: no per-token price. Electricity and hardware are not counted."
  }
 ]
}