{
 "object": "list",
 "endpoint": "https://api.revana.si/v1/chat/completions",
 "unit": "USD per million tokens",
 "checked": "2026-10-29",
 "models": [
  {
   "id": "claude-fable-5",
   "name": "Claude Fable 5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "The previous Fable, for long-running agentic work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3.5,
    "cached_input": 0.35,
    "cache_write": 4.375,
    "cache_write_1h": 7,
    "output": 17.5
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-fable-5-1",
   "name": "Claude Fable 5.1",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Anthropic's model for demanding reasoning and long-horizon agentic work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3.5,
    "cached_input": 0.0875,
    "cache_write": 4.375,
    "cache_write_1h": 7,
    "output": 17.5,
    "effort_max_multiplier": 3
   },
   "notes": "Reasoning tokens are billed as output tokens. A request at effort max is billed at 3× these rates. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-haiku-4-5-20251001",
   "name": "Claude Haiku 4.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Haiku 4.5 by Anthropic, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1,
    "cached_input": 0.1,
    "cache_write": 1.25,
    "cache_write_1h": 2,
    "output": 5
   }
  },
  {
   "id": "claude-haiku-4-5-20251001-thinking",
   "name": "Claude Haiku 4.5 (thinking)",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Haiku 4.5 (thinking) by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1,
    "cached_input": 1,
    "cache_write": 1,
    "cache_write_1h": 1,
    "output": 5
   }
  },
  {
   "id": "claude-haiku-5-5",
   "name": "Claude Haiku 5.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "For high-volume, latency-sensitive tasks such as classification, extraction and routing.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.035,
    "cached_input": 0.0035,
    "cache_write": 0.04375,
    "cache_write_1h": 0.07,
    "output": 0.175,
    "tiers": [
     {
      "prompt_tokens_above": 100000,
      "input": 0.175,
      "cached_input": 0.0175,
      "cache_write": 0.21875,
      "cache_write_1h": 0.35,
      "output": 0.875
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. When a request's prompt is over 100K tokens, cached tokens included, the whole request bills every token at 5× these rates. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-opus-4-5-20251101",
   "name": "Claude Opus 4.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Opus 4.5 by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 5,
    "cached_input": 5,
    "cache_write": 5,
    "cache_write_1h": 5,
    "output": 25
   }
  },
  {
   "id": "claude-opus-4-5-20251101-thinking",
   "name": "Claude Opus 4.5 (thinking)",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Opus 4.5 (thinking) by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 5,
    "cached_input": 5,
    "cache_write": 5,
    "cache_write_1h": 5,
    "output": 25
   }
  },
  {
   "id": "claude-opus-4-6",
   "name": "Claude Opus 4.6",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Opus 4.6 by Anthropic, through an OpenAI-compatible chat completions API.",
   "context_tokens": 1000000,
   "max_output_tokens": 1000000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 5,
    "cached_input": 0.5,
    "cache_write": 6.25,
    "cache_write_1h": 6.25,
    "output": 10
   }
  },
  {
   "id": "claude-opus-4-6-thinking",
   "name": "Claude Opus 4.6 (thinking)",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Opus 4.6 (thinking) by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 5,
    "cached_input": 5,
    "cache_write": 5,
    "cache_write_1h": 5,
    "output": 25
   }
  },
  {
   "id": "claude-opus-4-7",
   "name": "Claude Opus 4.7",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Opus 4.7 by Anthropic, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 5,
    "cached_input": 0.5,
    "cache_write": 6.25,
    "cache_write_1h": 10,
    "output": 25
   }
  },
  {
   "id": "claude-opus-4-8",
   "name": "Claude Opus 4.8",
   "maker": "Anthropic",
   "kind": "text",
   "description": "The previous Opus generation, for complex coding and agent work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.75,
    "cached_input": 0.175,
    "cache_write": 2.1875,
    "cache_write_1h": 3.5,
    "output": 8.75
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-opus-5",
   "name": "Claude Opus 5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "For complex agentic coding and enterprise work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.75,
    "cached_input": 0.175,
    "cache_write": 2.1875,
    "cache_write_1h": 3.5,
    "output": 8.75
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-opus-5-5",
   "name": "Claude Opus 5.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "For long-running agentic coding and knowledge work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.4,
    "cached_input": 0.07,
    "cache_write": 1.75,
    "cache_write_1h": 2.8,
    "output": 7
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-sonnet-4-5-20250929",
   "name": "Claude Sonnet 4.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Sonnet 4.5 by Anthropic, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3,
    "cached_input": 0.3,
    "cache_write": 3.75,
    "cache_write_1h": 6,
    "output": 15
   }
  },
  {
   "id": "claude-sonnet-4-5-20250929-thinking",
   "name": "Claude Sonnet 4.5 (thinking)",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Sonnet 4.5 (thinking) by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3,
    "cached_input": 3,
    "cache_write": 3,
    "cache_write_1h": 3,
    "output": 15
   }
  },
  {
   "id": "claude-sonnet-4-6",
   "name": "Claude Sonnet 4.6",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Sonnet 4.6 by Anthropic, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3,
    "cached_input": 0.3,
    "cache_write": 3.75,
    "cache_write_1h": 6,
    "output": 15
   }
  },
  {
   "id": "claude-sonnet-4-6-thinking",
   "name": "Claude Sonnet 4.6 (thinking)",
   "maker": "Anthropic",
   "kind": "text",
   "description": "Claude Sonnet 4.6 (thinking) by Anthropic, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 3,
    "cached_input": 3,
    "cache_write": 3,
    "cache_write_1h": 3,
    "output": 15
   }
  },
  {
   "id": "claude-sonnet-5",
   "name": "Claude Sonnet 5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "The best combination of speed and intelligence in the Claude lineup.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.7,
    "cached_input": 0.07,
    "cache_write": 0.875,
    "cache_write_1h": 1.4,
    "output": 3.5
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "claude-sonnet-5-5",
   "name": "Claude Sonnet 5.5",
   "maker": "Anthropic",
   "kind": "text",
   "description": "The best combination of speed and intelligence, as Anthropic's latest Sonnet.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.7,
    "cached_input": 0.035,
    "cache_write": 0.875,
    "cache_write_1h": 1.4,
    "output": 3.5
   },
   "notes": "Reasoning tokens are billed as output tokens. A 1-hour cache write is billed at twice the input rate."
  },
  {
   "id": "deepseek-r1",
   "name": "DeepSeek R1",
   "maker": "DeepSeek",
   "kind": "text",
   "description": "DeepSeek R1 by DeepSeek, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.56,
    "cached_input": 0.56,
    "cache_write": 0.56,
    "cache_write_1h": 0.56,
    "output": 2.24
   }
  },
  {
   "id": "deepseek-v4-flash",
   "name": "DeepSeek V4 Flash",
   "maker": "DeepSeek",
   "kind": "text",
   "description": "DeepSeek V4 Flash by DeepSeek, through an OpenAI-compatible chat completions API.",
   "context_tokens": 1000000,
   "max_output_tokens": 393216,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.428571,
    "cached_input": 0.042857,
    "cache_write": 0.428571,
    "cache_write_1h": 0.428571,
    "output": 1.285714
   }
  },
  {
   "id": "deepseek-v4-pro",
   "name": "DeepSeek V4 Pro",
   "maker": "DeepSeek",
   "kind": "text",
   "description": "DeepSeek's strongest model, upgraded for agent work.",
   "context_tokens": 1000000,
   "max_output_tokens": 393220,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.396,
    "cached_input": 0.0132,
    "cache_write": 0.396,
    "cache_write_1h": 0.792,
    "output": 1.188,
    "peak_multiplier": 2,
    "peak_hours": "weekdays 09:00-12:00 and 14:00-18:00 Beijing time (UTC+8)"
   },
   "notes": "Weekdays 09:00–12:00 and 14:00–18:00 Beijing time are billed at twice these rates. Reasoning tokens are billed as output tokens."
  },
  {
   "id": "deepseek-v4.1-flash",
   "name": "DeepSeek V4.1 Flash",
   "maker": "DeepSeek",
   "kind": "text",
   "description": "DeepSeek's fast, low-cost model, with native image understanding.",
   "context_tokens": 1000000,
   "max_output_tokens": 393220,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.09,
    "cached_input": 0.0018,
    "cache_write": 0.09,
    "cache_write_1h": 0.18,
    "output": 0.36,
    "peak_multiplier": 2,
    "peak_hours": "weekdays 09:00-12:00 and 14:00-18:00 Beijing time (UTC+8)"
   },
   "notes": "Weekdays 09:00–12:00 and 14:00–18:00 Beijing time are billed at twice these rates. Reasoning tokens are billed as output tokens."
  },
  {
   "id": "gemini-2.5-flash",
   "name": "Gemini 2.5 Flash",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Flash by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 2.4999
   }
  },
  {
   "id": "gemini-2.5-flash-nothinking",
   "name": "Gemini 2.5 Flash (no thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Flash (no thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 2.4999
   }
  },
  {
   "id": "gemini-2.5-flash-thinking",
   "name": "Gemini 2.5 Flash (thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Flash (thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 2.4999
   }
  },
  {
   "id": "gemini-2.5-flash-lite",
   "name": "Gemini 2.5 Flash Lite",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Flash Lite by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.1,
    "cached_input": 0.1,
    "cache_write": 0.1,
    "cache_write_1h": 0.1,
    "output": 0.4
   }
  },
  {
   "id": "gemini-2.5-pro",
   "name": "Gemini 2.5 Pro",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Pro by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 10
   }
  },
  {
   "id": "gemini-2.5-pro-nothinking",
   "name": "Gemini 2.5 Pro (no thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Pro (no thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 10
   }
  },
  {
   "id": "gemini-2.5-pro-thinking",
   "name": "Gemini 2.5 Pro (thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 2.5 Pro (thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 10
   }
  },
  {
   "id": "gemini-3-flash-preview",
   "name": "Gemini 3 Flash Preview",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3 Flash Preview by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.5,
    "cached_input": 0.5,
    "cache_write": 0.5,
    "cache_write_1h": 0.5,
    "output": 3
   }
  },
  {
   "id": "gemini-3-flash-preview-nothinking",
   "name": "Gemini 3 Flash Preview (no thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3 Flash Preview (no thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.5,
    "cached_input": 0.5,
    "cache_write": 0.5,
    "cache_write_1h": 0.5,
    "output": 3
   }
  },
  {
   "id": "gemini-3-flash-preview-thinking",
   "name": "Gemini 3 Flash Preview (thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3 Flash Preview (thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.5,
    "cached_input": 0.5,
    "cache_write": 0.5,
    "cache_write_1h": 0.5,
    "output": 3
   }
  },
  {
   "id": "gemini-3-pro-preview",
   "name": "Gemini 3 Pro Preview",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3 Pro Preview by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 2,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 12
   }
  },
  {
   "id": "gemini-3-pro-preview-thinking",
   "name": "Gemini 3 Pro Preview (thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3 Pro Preview (thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 2,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 12
   }
  },
  {
   "id": "gemini-3.1-flash-lite-preview",
   "name": "Gemini 3.1 Flash Lite Preview",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.1 Flash Lite Preview by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.25,
    "cached_input": 0.25,
    "cache_write": 0.25,
    "cache_write_1h": 0.25,
    "output": 1.5
   }
  },
  {
   "id": "gemini-3.1-pro-preview",
   "name": "Gemini 3.1 Pro Preview",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.1 Pro Preview by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 2,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 12
   }
  },
  {
   "id": "gemini-3.1-pro-preview-thinking",
   "name": "Gemini 3.1 Pro Preview (thinking)",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.1 Pro Preview (thinking) by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 2,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 12
   }
  },
  {
   "id": "gemini-3.5-flash",
   "name": "Gemini 3.5 Flash",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.5 Flash by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.5,
    "cached_input": 1.5,
    "cache_write": 1.5,
    "cache_write_1h": 1.5,
    "output": 9
   }
  },
  {
   "id": "gemini-3.5-flash-lite",
   "name": "Gemini 3.5 Flash Lite",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.5 Flash Lite by Google, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 2.499
   }
  },
  {
   "id": "gemini-3.6-flash",
   "name": "Gemini 3.6 Flash",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.6 Flash by Google, through an OpenAI-compatible chat completions API.",
   "context_tokens": 1050000,
   "max_output_tokens": 65536,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.5,
    "cached_input": 0.15,
    "cache_write": 1.5,
    "cache_write_1h": 1.5,
    "output": 7.5
   }
  },
  {
   "id": "gemini-3.7-flash",
   "name": "Gemini 3.7 Flash",
   "maker": "Google",
   "kind": "text",
   "description": "Gemini 3.7 Flash by Google, through an OpenAI-compatible chat completions API.",
   "context_tokens": 1048576,
   "max_output_tokens": 65536,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.75,
    "cached_input": 0.075,
    "cache_write": 0.75,
    "cache_write_1h": 0.75,
    "output": 3.75
   }
  },
  {
   "id": "gemini-3.8-flash",
   "name": "Gemini 3.8 Flash",
   "maker": "Google",
   "kind": "text",
   "description": "Google's fast, low-cost Gemini model for everyday text and image tasks.",
   "context_tokens": 1000000,
   "max_output_tokens": 64000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.225,
    "cached_input": 0.0225,
    "cache_write": 0.225,
    "cache_write_1h": 0.45,
    "output": 1.125
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "gemini-4-argon",
   "name": "Gemini 4 Argon",
   "maker": "Google",
   "kind": "text",
   "description": "Google's flagship Gemini model for complex reasoning, coding and long-context work.",
   "context_tokens": 1000000,
   "max_output_tokens": 64000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.6,
    "cached_input": 0.03,
    "cache_write": 0.6,
    "cache_write_1h": 1.2,
    "output": 3
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "kimi-k2.5",
   "name": "Kimi K2.5",
   "maker": "Kimi",
   "kind": "text",
   "description": "Kimi K2.5 by Kimi, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.514,
    "cached_input": 0.514,
    "cache_write": 0.514,
    "cache_write_1h": 0.514,
    "output": 0.6939
   }
  },
  {
   "id": "kimi-k2.6",
   "name": "Kimi K2.6",
   "maker": "Kimi",
   "kind": "text",
   "description": "Kimi's general model for chat and agent tasks.",
   "context_tokens": 256000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.57,
    "cached_input": 0.096,
    "cache_write": 0.57,
    "cache_write_1h": 1.14,
    "output": 2.4
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "kimi-k2.7-code",
   "name": "Kimi K2.7 Code",
   "maker": "Kimi",
   "kind": "text",
   "description": "Kimi's dedicated coding model.",
   "context_tokens": 256000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.57,
    "cached_input": 0.114,
    "cache_write": 0.57,
    "cache_write_1h": 1.14,
    "output": 2.4
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "kimi-k3",
   "name": "Kimi K3",
   "maker": "Kimi",
   "kind": "text",
   "description": "Kimi's most capable model, with visual understanding.",
   "context_tokens": 1000000,
   "max_output_tokens": 1000000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.8,
    "cached_input": 0.18,
    "cache_write": 1.8,
    "cache_write_1h": 3.6,
    "output": 9
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "minimax-m2.5",
   "name": "MiniMax M2.5",
   "maker": "MiniMax",
   "kind": "text",
   "description": "MiniMax M2.5 by MiniMax, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 1.2
   }
  },
  {
   "id": "minimax-m3",
   "name": "MiniMax M3",
   "maker": "MiniMax",
   "kind": "text",
   "description": "MiniMax M3 by MiniMax, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.3,
    "cached_input": 0.3,
    "cache_write": 0.3,
    "cache_write_1h": 0.3,
    "output": 1.2
   }
  },
  {
   "id": "gpt-4.1",
   "name": "GPT-4.1",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-4.1 by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 0.5,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 8
   }
  },
  {
   "id": "gpt-4.1-mini",
   "name": "GPT-4.1 mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-4.1 mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.4,
    "cached_input": 0.1,
    "cache_write": 0.4,
    "cache_write_1h": 0.4,
    "output": 1.6
   }
  },
  {
   "id": "gpt-4.1-nano",
   "name": "GPT-4.1 nano",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-4.1 nano by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.1,
    "cached_input": 0.025,
    "cache_write": 0.1,
    "cache_write_1h": 0.1,
    "output": 0.4
   }
  },
  {
   "id": "gpt-4o",
   "name": "GPT-4o",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-4o by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2.5,
    "cached_input": 1.25,
    "cache_write": 2.5,
    "cache_write_1h": 2.5,
    "output": 10
   }
  },
  {
   "id": "gpt-4o-mini",
   "name": "GPT-4o mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-4o mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.15,
    "cached_input": 0.15,
    "cache_write": 0.15,
    "cache_write_1h": 0.15,
    "output": 0.6
   }
  },
  {
   "id": "gpt-5",
   "name": "GPT-5",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5 by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 0.125,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 10
   }
  },
  {
   "id": "gpt-5-mini",
   "name": "GPT-5 mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5 mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.25,
    "cached_input": 0.025,
    "cache_write": 0.25,
    "cache_write_1h": 0.25,
    "output": 2
   }
  },
  {
   "id": "gpt-5-nano",
   "name": "GPT-5 nano",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5 nano by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.05,
    "cached_input": 0.005,
    "cache_write": 0.05,
    "cache_write_1h": 0.05,
    "output": 0.4
   }
  },
  {
   "id": "gpt-5.1",
   "name": "GPT-5.1",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.1 by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 0.125,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 10
   }
  },
  {
   "id": "gpt-5.2",
   "name": "GPT-5.2",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.2 by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.75,
    "cached_input": 0.175,
    "cache_write": 1.75,
    "cache_write_1h": 1.75,
    "output": 14
   }
  },
  {
   "id": "gpt-5.4",
   "name": "GPT-5.4",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.4 by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 1000000,
   "max_output_tokens": 12800,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2.5,
    "cached_input": 0.25,
    "cache_write": 2.5,
    "cache_write_1h": 2.5,
    "output": 15,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 5,
      "cached_input": 0.5,
      "cache_write": 5,
      "cache_write_1h": 5,
      "output": 22.5
     }
    ]
   }
  },
  {
   "id": "gpt-5.4-mini",
   "name": "GPT-5.4 mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.4 mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.75,
    "cached_input": 0.075,
    "cache_write": 0.75,
    "cache_write_1h": 0.75,
    "output": 4.5
   }
  },
  {
   "id": "gpt-5.4-nano",
   "name": "GPT-5.4 nano",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.4 nano by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.2,
    "cached_input": 0.02,
    "cache_write": 0.2,
    "cache_write_1h": 0.2,
    "output": 1.25
   }
  },
  {
   "id": "gpt-5.5",
   "name": "GPT-5.5",
   "maker": "OpenAI",
   "kind": "text",
   "description": "A flagship for coding and the most complex professional work.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.15,
    "cached_input": 0.115,
    "cache_write": 1.15,
    "cache_write_1h": 2.3,
    "output": 6.9,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 2.3,
      "cached_input": 0.23,
      "cache_write": 2.3,
      "cache_write_1h": 4.6,
      "output": 10.35
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2.5× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-5.6-luna",
   "name": "GPT-5.6 Luna",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-5.6 Luna by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 922000,
   "max_output_tokens": 128000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.2,
    "cached_input": 0.02,
    "cache_write": 0.25,
    "cache_write_1h": 0.5,
    "output": 1.2,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 0.4,
      "cached_input": 0.04,
      "cache_write": 0.5,
      "cache_write_1h": 1,
      "output": 1.8
     }
    ]
   }
  },
  {
   "id": "gpt-5.6-sol",
   "name": "GPT-5.6 Sol",
   "maker": "OpenAI",
   "kind": "text",
   "description": "The GPT-5.6 flagship for complex professional work.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.92,
    "cached_input": 0.092,
    "cache_write": 1.15,
    "cache_write_1h": 1.84,
    "output": 4.6,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 1.84,
      "cached_input": 0.184,
      "cache_write": 2.3,
      "cache_write_1h": 3.68,
      "output": 6.9
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-5.6-terra",
   "name": "GPT-5.6 Terra",
   "maker": "OpenAI",
   "kind": "text",
   "description": "The GPT-5.6 model that balances intelligence and cost.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.46,
    "cached_input": 0.046,
    "cache_write": 0.575,
    "cache_write_1h": 0.92,
    "output": 2.76,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 0.92,
      "cached_input": 0.092,
      "cache_write": 1.15,
      "cache_write_1h": 1.84,
      "output": 4.14
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-6-astra",
   "name": "GPT-6 Astra",
   "maker": "OpenAI",
   "kind": "text",
   "description": "OpenAI's most capable model, built for the hardest end-to-end work.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2.3,
    "cached_input": 0.23,
    "cache_write": 2.875,
    "cache_write_1h": 4.6,
    "output": 11.5,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 4.6,
      "cached_input": 0.46,
      "cache_write": 5.75,
      "cache_write_1h": 9.2,
      "output": 17.25
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-6-luna",
   "name": "GPT-6 Luna",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-6 Luna by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 922000,
   "max_output_tokens": 12800,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.1,
    "cached_input": 0.01,
    "cache_write": 0.125,
    "cache_write_1h": 0.25,
    "output": 0.5,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 0.2,
      "cached_input": 0.02,
      "cache_write": 0.25,
      "cache_write_1h": 0.5,
      "output": 0.75
     }
    ]
   }
  },
  {
   "id": "gpt-6-sol",
   "name": "GPT-6 Sol",
   "maker": "OpenAI",
   "kind": "text",
   "description": "The GPT-6 model for complex coding and agentic workflows.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.46,
    "cached_input": 0.046,
    "cache_write": 0.575,
    "cache_write_1h": 0.92,
    "output": 2.3,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 0.92,
      "cached_input": 0.092,
      "cache_write": 1.15,
      "cache_write_1h": 1.84,
      "output": 3.45
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-6.1-sol",
   "name": "GPT-6.1 Sol",
   "maker": "OpenAI",
   "kind": "text",
   "description": "Near-Astra performance for complex coding, computer use and professional work.",
   "context_tokens": 1050000,
   "max_output_tokens": 128000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.46,
    "cached_input": 0.023,
    "cache_write": 0.575,
    "cache_write_1h": 0.92,
    "output": 2.3,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 0.92,
      "cached_input": 0.046,
      "cache_write": 1.15,
      "cache_write_1h": 1.84,
      "output": 3.45
     }
    ]
   },
   "notes": "Reasoning tokens are billed as output tokens. Fast mode (service_tier priority) bills every token at 2× these rates. When a request's prompt is over 272K tokens, cached tokens included, the whole request bills its output at 1.5× these rates and every other token at 2×. Fast mode and the long-context rates multiply."
  },
  {
   "id": "gpt-6.1-terra",
   "name": "GPT-6.1 Terra",
   "maker": "OpenAI",
   "kind": "text",
   "description": "GPT-6.1 Terra by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 922000,
   "max_output_tokens": 12800,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1,
    "cached_input": 0.05,
    "cache_write": 1.25,
    "cache_write_1h": 2.5,
    "output": 5,
    "tiers": [
     {
      "prompt_tokens_above": 272000,
      "input": 2,
      "cached_input": 0.1,
      "cache_write": 2.5,
      "cache_write_1h": 5,
      "output": 7.5
     }
    ]
   }
  },
  {
   "id": "o3",
   "name": "o3",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o3 by OpenAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 2,
    "cached_input": 2,
    "cache_write": 2,
    "cache_write_1h": 2,
    "output": 8
   }
  },
  {
   "id": "o3-mini",
   "name": "o3-mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o3-mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.1,
    "cached_input": 0.55,
    "cache_write": 1.1,
    "cache_write_1h": 1.1,
    "output": 4.4
   }
  },
  {
   "id": "o3-mini-high",
   "name": "o3-mini (high)",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o3-mini (high) by OpenAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.1,
    "cached_input": 1.1,
    "cache_write": 1.1,
    "cache_write_1h": 1.1,
    "output": 4.4
   }
  },
  {
   "id": "o3-mini-low",
   "name": "o3-mini (low)",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o3-mini (low) by OpenAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.1,
    "cached_input": 1.1,
    "cache_write": 1.1,
    "cache_write_1h": 1.1,
    "output": 4.4
   }
  },
  {
   "id": "o3-mini-medium",
   "name": "o3-mini (medium)",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o3-mini (medium) by OpenAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.1,
    "cached_input": 1.1,
    "cache_write": 1.1,
    "cache_write_1h": 1.1,
    "output": 4.4
   }
  },
  {
   "id": "o4-mini",
   "name": "o4-mini",
   "maker": "OpenAI",
   "kind": "text",
   "description": "o4-mini by OpenAI, through an OpenAI-compatible chat completions API.",
   "context_tokens": 128000,
   "max_output_tokens": 16000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.1,
    "cached_input": 0.275,
    "cache_write": 1.1,
    "cache_write_1h": 1.1,
    "output": 4.4
   }
  },
  {
   "id": "qwen3.6-flash",
   "name": "Qwen3.6-Flash",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.6-Flash by Qwen, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.1714,
    "cached_input": 0.1714,
    "cache_write": 0.1714,
    "cache_write_1h": 0.1714,
    "output": 1.0284
   }
  },
  {
   "id": "qwen3.6-plus",
   "name": "Qwen3.6-Plus",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.6-Plus by Qwen, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.2858,
    "cached_input": 0.2858,
    "cache_write": 0.2858,
    "cache_write_1h": 0.2858,
    "output": 1.7148
   }
  },
  {
   "id": "qwen3.7-flash",
   "name": "Qwen3.7-Flash",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.7-Flash by Qwen, through an OpenAI-compatible chat completions API.",
   "context_tokens": 983616,
   "max_output_tokens": 131072,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.028571,
    "cached_input": 0.005714,
    "cache_write": 0.035714,
    "cache_write_1h": 0.035714,
    "output": 0.114286
   }
  },
  {
   "id": "qwen3.7-max",
   "name": "Qwen3.7-Max",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.7-Max by Qwen, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.7142,
    "cached_input": 1.7142,
    "cache_write": 1.7142,
    "cache_write_1h": 1.7142,
    "output": 5.1426
   }
  },
  {
   "id": "qwen3.7-plus",
   "name": "Qwen3.7-Plus",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.7-Plus by Qwen, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.2858,
    "cached_input": 0.2858,
    "cache_write": 0.2858,
    "cache_write_1h": 0.2858,
    "output": 1.1432
   }
  },
  {
   "id": "qwen3.8-2.4t-a95b",
   "name": "Qwen3.8 2.4T-A95B",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.8 2.4T-A95B by Qwen, through an OpenAI-compatible chat completions API.",
   "context_tokens": 983616,
   "max_output_tokens": 131072,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.714286,
    "cached_input": 0.214286,
    "cache_write": 2.142857,
    "cache_write_1h": 2.142857,
    "output": 5.142857
   }
  },
  {
   "id": "qwen3.8-27b",
   "name": "Qwen3.8 27B",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.8 27B by Qwen, through an OpenAI-compatible chat completions API.",
   "context_tokens": 983616,
   "max_output_tokens": 131072,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.428571,
    "cached_input": 0.085714,
    "cache_write": 0.535714,
    "cache_write_1h": 0.535714,
    "output": 1.714286
   }
  },
  {
   "id": "qwen3.8-flash",
   "name": "Qwen3.8-Flash",
   "maker": "Qwen",
   "kind": "text",
   "description": "Qwen3.8-Flash by Qwen, through an OpenAI-compatible chat completions API.",
   "context_tokens": 983616,
   "max_output_tokens": 131072,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.114286,
    "cached_input": 0.014286,
    "cache_write": 0.178571,
    "cache_write_1h": 0.178571,
    "output": 0.385714
   }
  },
  {
   "id": "qwen3.8-max",
   "name": "Qwen3.8-Max",
   "maker": "Qwen",
   "kind": "text",
   "description": "Alibaba's flagship Qwen model for complex reasoning, coding and agent work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.2,
    "cached_input": 0.15,
    "cache_write": 1.5,
    "cache_write_1h": 2.4,
    "output": 3.6
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "step-3.7-flash",
   "name": "Step 3.7 Flash",
   "maker": "StepFun",
   "kind": "text",
   "description": "Step 3.7 Flash by StepFun, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.1928,
    "cached_input": 0.1928,
    "cache_write": 0.1928,
    "cache_write_1h": 0.1928,
    "output": 1.1568
   }
  },
  {
   "id": "grok-4.3",
   "name": "Grok 4.3",
   "maker": "xAI",
   "kind": "text",
   "description": "Grok 4.3 by xAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 2.5
   }
  },
  {
   "id": "grok-4.5",
   "name": "Grok 4.5",
   "maker": "xAI",
   "kind": "text",
   "description": "xAI's coding model for agentic software development, engineering and workflow tasks.",
   "context_tokens": 500000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.6,
    "cached_input": 0.09,
    "cache_write": 0.6,
    "cache_write_1h": 1.2,
    "output": 1.8
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "grok-4.6",
   "name": "Grok 4.6",
   "maker": "xAI",
   "kind": "text",
   "description": "xAI's frontier model for coding, agentic tasks and knowledge work.",
   "context_tokens": 500000,
   "max_output_tokens": 12800,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.6,
    "cached_input": 0.15,
    "cache_write": 0.6,
    "cache_write_1h": 1.2,
    "output": 1.8
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "grok-4.7",
   "name": "Grok 4.7",
   "maker": "xAI",
   "kind": "text",
   "description": "xAI's most capable model for coding and knowledge work.",
   "context_tokens": 500000,
   "max_output_tokens": 12800,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.6,
    "cached_input": 0.15,
    "cache_write": 0.6,
    "cache_write_1h": 1.2,
    "output": 1.8
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "grok-4.20-0309-non-reasoning",
   "name": "Grok 4.20 (non-reasoning)",
   "maker": "xAI",
   "kind": "text",
   "description": "Grok 4.20 (non-reasoning) by xAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 2.5
   }
  },
  {
   "id": "grok-4.20-0309-reasoning",
   "name": "Grok 4.20 (reasoning)",
   "maker": "xAI",
   "kind": "text",
   "description": "Grok 4.20 (reasoning) by xAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1.25,
    "cached_input": 1.25,
    "cache_write": 1.25,
    "cache_write_1h": 1.25,
    "output": 2.5
   }
  },
  {
   "id": "grok-build-0.1",
   "name": "Grok Build 0.1",
   "maker": "xAI",
   "kind": "text",
   "description": "Grok Build 0.1 by xAI, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1,
    "cached_input": 1,
    "cache_write": 1,
    "cache_write_1h": 1,
    "output": 2
   }
  },
  {
   "id": "glm-5",
   "name": "GLM-5",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "GLM-5 by Zhipu GLM, through an OpenAI-compatible chat completions API.",
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 1,
    "cached_input": 1,
    "cache_write": 1,
    "cache_write_1h": 1,
    "output": 1.6
   }
  },
  {
   "id": "glm-5.1",
   "name": "GLM-5.1",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "Z.ai's earlier general-purpose GLM for chat and coding.",
   "context_tokens": 200000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.84,
    "cached_input": 0.156,
    "cache_write": 0.84,
    "cache_write_1h": 1.68,
    "output": 2.64
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "glm-5.2",
   "name": "GLM-5.2",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "Z.ai's general-purpose GLM for reasoning and coding.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.84,
    "cached_input": 0.156,
    "cache_write": 0.84,
    "cache_write_1h": 1.68,
    "output": 2.64
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "glm-5.3",
   "name": "GLM-5.3",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "Z.ai's flagship for complex software engineering and long-horizon agent work.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.84,
    "cached_input": 0.156,
    "cache_write": 0.84,
    "cache_write_1h": 1.68,
    "output": 2.64
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "glm-5.3-flash",
   "name": "GLM-5.3 Flash",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "The lowest-cost GLM-5, and the first in the series to read images.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 2,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.09,
    "cached_input": 0.018,
    "cache_write": 0.09,
    "cache_write_1h": 0.18,
    "output": 0.3
   },
   "notes": "Reasoning tokens are billed as output tokens."
  },
  {
   "id": "glm-5.3-flashx",
   "name": "GLM-5.3 FlashX",
   "maker": "Zhipu GLM",
   "kind": "text",
   "description": "GLM-5.3 Flash at about 200 tokens a second.",
   "context_tokens": 1000000,
   "max_output_tokens": 128000,
   "routes": 1,
   "price": {
    "unit": "per_million_tokens",
    "currency": "USD",
    "input": 0.222,
    "cached_input": 0.045,
    "cache_write": 0.222,
    "cache_write_1h": 0.444,
    "output": 0.75
   },
   "notes": "Reasoning tokens are billed as output tokens."
  }
 ]
}