{
 "date": "2026-08-10",
 "source": "LiteLLM public dataset, captured into our archive; see /index/methodology",
 "models": {
  "claude-fable-5": {
   "input_cost_per_token": 0.00001,
   "output_cost_per_token": 0.00005,
   "cache_read_input_token_cost": 0.000001
  },
  "claude-opus-5": {
   "input_cost_per_token": 0.000005,
   "output_cost_per_token": 0.000025,
   "cache_read_input_token_cost": 5e-7
  },
  "claude-sonnet-5": {
   "input_cost_per_token": 0.000002,
   "output_cost_per_token": 0.00001,
   "cache_read_input_token_cost": 2e-7
  },
  "claude-haiku-4-5": {
   "input_cost_per_token": 0.000001,
   "output_cost_per_token": 0.000005,
   "cache_read_input_token_cost": 1e-7
  },
  "deepseek-v4-pro": {
   "input_cost_per_token": 4.35e-7,
   "output_cost_per_token": 8.7e-7,
   "cache_read_input_token_cost": 3.625e-9
  },
  "deepseek-v4-flash": {
   "input_cost_per_token": 1.4e-7,
   "output_cost_per_token": 2.8e-7,
   "cache_read_input_token_cost": 2.8e-9
  },
  "gemini/gemini-2.5-pro": {
   "input_cost_per_token": 0.00000125,
   "output_cost_per_token": 0.00001,
   "cache_read_input_token_cost": 1.25e-7
  },
  "gemini/gemini-3.5-flash": {
   "input_cost_per_token": 0.0000015,
   "output_cost_per_token": 0.000009,
   "cache_read_input_token_cost": 1.5e-7
  },
  "gemini/gemini-3.6-flash": {
   "input_cost_per_token": 0.0000015,
   "output_cost_per_token": 0.0000075,
   "cache_read_input_token_cost": 1.5e-7
  },
  "gemini/gemini-3.5-flash-lite": {
   "input_cost_per_token": 3e-7,
   "output_cost_per_token": 0.0000025,
   "cache_read_input_token_cost": 3e-8
  },
  "gemini/gemini-3.1-flash-lite": {
   "input_cost_per_token": 2.5e-7,
   "output_cost_per_token": 0.0000015,
   "cache_read_input_token_cost": 2.5e-8
  },
  "gemini/gemini-2.5-flash-lite": {
   "input_cost_per_token": 1e-7,
   "output_cost_per_token": 4e-7,
   "cache_read_input_token_cost": 1e-8
  },
  "gemini/gemini-2.0-flash-lite-001": {
   "input_cost_per_token": 7.5e-8,
   "output_cost_per_token": 3e-7,
   "cache_read_input_token_cost": 1.875e-8
  },
  "mistral/magistral-medium-1-2-2509": {
   "input_cost_per_token": 0.000002,
   "output_cost_per_token": 0.000005
  },
  "mistral/mistral-medium-2508": {
   "input_cost_per_token": 4e-7,
   "output_cost_per_token": 0.000002
  },
  "mistral/mistral-large-2512": {
   "input_cost_per_token": 5e-7,
   "output_cost_per_token": 0.0000015
  },
  "mistral/codestral-2508": {
   "input_cost_per_token": 3e-7,
   "output_cost_per_token": 9e-7
  },
  "mistral/labs-devstral-small-2512": {
   "input_cost_per_token": 1e-7,
   "output_cost_per_token": 3e-7
  },
  "mistral/ministral-3-14b-2512": {
   "input_cost_per_token": 2e-7,
   "output_cost_per_token": 2e-7
  },
  "mistral/mistral-small-3-2-2506": {
   "input_cost_per_token": 6e-8,
   "output_cost_per_token": 1.8e-7
  },
  "mistral/ministral-3-8b-2512": {
   "input_cost_per_token": 1.5e-7,
   "output_cost_per_token": 1.5e-7
  },
  "mistral/ministral-3-3b-2512": {
   "input_cost_per_token": 1e-7,
   "output_cost_per_token": 1e-7
  },
  "gpt-5.6": {
   "input_cost_per_token": 0.000005,
   "output_cost_per_token": 0.00003,
   "cache_read_input_token_cost": 5e-7
  },
  "gpt-5.3-chat-latest": {
   "input_cost_per_token": 0.00000175,
   "output_cost_per_token": 0.000014,
   "cache_read_input_token_cost": 1.75e-7
  },
  "gpt-5.6-terra": {
   "input_cost_per_token": 0.000002,
   "output_cost_per_token": 0.000012,
   "cache_read_input_token_cost": 2e-7
  },
  "gpt-5-chat": {
   "input_cost_per_token": 0.00000125,
   "output_cost_per_token": 0.00001,
   "cache_read_input_token_cost": 1.25e-7
  },
  "gpt-5.4-mini": {
   "input_cost_per_token": 7.5e-7,
   "output_cost_per_token": 0.0000045,
   "cache_read_input_token_cost": 7.5e-8
  },
  "gpt-5-mini": {
   "input_cost_per_token": 2.5e-7,
   "output_cost_per_token": 0.000002,
   "cache_read_input_token_cost": 2.5e-8
  },
  "gpt-5.4-nano": {
   "input_cost_per_token": 2e-7,
   "output_cost_per_token": 0.00000125,
   "cache_read_input_token_cost": 2e-8
  },
  "gpt-5.6-luna": {
   "input_cost_per_token": 2e-7,
   "output_cost_per_token": 0.0000012,
   "cache_read_input_token_cost": 2e-8
  },
  "gpt-5-nano": {
   "input_cost_per_token": 5e-8,
   "output_cost_per_token": 4e-7,
   "cache_read_input_token_cost": 5e-9
  },
  "perplexity/sonar-pro": {
   "input_cost_per_token": 0.000003,
   "output_cost_per_token": 0.000015
  },
  "perplexity/sonar-reasoning-pro": {
   "input_cost_per_token": 0.000002,
   "output_cost_per_token": 0.000008
  },
  "perplexity/sonar-reasoning": {
   "input_cost_per_token": 0.000001,
   "output_cost_per_token": 0.000005
  },
  "perplexity/sonar": {
   "input_cost_per_token": 0.000001,
   "output_cost_per_token": 0.000001
  },
  "xai/grok-4": {
   "input_cost_per_token": 0.000003,
   "output_cost_per_token": 0.000015
  },
  "xai/grok-4.5": {
   "input_cost_per_token": 0.000002,
   "output_cost_per_token": 0.000006,
   "cache_read_input_token_cost": 5e-7
  },
  "xai/grok-3-mini-fast": {
   "input_cost_per_token": 6e-7,
   "output_cost_per_token": 0.000004,
   "cache_read_input_token_cost": 1.5e-7
  },
  "xai/grok-4.3": {
   "input_cost_per_token": 0.00000125,
   "output_cost_per_token": 0.0000025,
   "cache_read_input_token_cost": 2e-7
  },
  "xai/grok-code-fast": {
   "input_cost_per_token": 2e-7,
   "output_cost_per_token": 0.0000015,
   "cache_read_input_token_cost": 2e-8
  },
  "xai/grok-3-mini": {
   "input_cost_per_token": 3e-7,
   "output_cost_per_token": 5e-7,
   "cache_read_input_token_cost": 7.5e-8
  },
  "xai/grok-4-1-fast": {
   "input_cost_per_token": 2e-7,
   "output_cost_per_token": 5e-7,
   "cache_read_input_token_cost": 5e-8
  }
 }
}