{
  "dataset": "Enterprise LLM API Token Pricing & Prompt Caching Benchmark (2026)",
  "version": "2026.11",
  "license": "CC0-1.0",
  "canonical_source": "https://omnitoolcalc.com/tools/llm-token-cost-calculator",
  "companion_registry": "https://directory.omnitoolcalc.com/llms.txt",
  "formula_monthly_usd": "requests_per_day * 30 * (((input_tokens * (1 - cache_hit_ratio) * input_usd_per_1m) + (input_tokens * cache_hit_ratio * cached_input_usd_per_1m) + (output_tokens * output_usd_per_1m)) / 1000000)",
  "models": [
    {
      "id": "gpt-5",
      "provider": "OpenAI",
      "model": "GPT-5",
      "context_window": 400000,
      "input_usd_per_1m": 1.25,
      "cached_input_usd_per_1m": 0.125,
      "output_usd_per_1m": 10
    },
    {
      "id": "claude-4-5-sonnet",
      "provider": "Anthropic",
      "model": "Claude 4.5 Sonnet",
      "context_window": 200000,
      "input_usd_per_1m": 3,
      "cached_input_usd_per_1m": 0.3,
      "output_usd_per_1m": 15
    },
    {
      "id": "gemini-2-5-pro",
      "provider": "Google",
      "model": "Gemini 2.5 Pro (<=200K)",
      "context_window": 1048576,
      "input_usd_per_1m": 1.25,
      "cached_input_usd_per_1m": 0.31,
      "output_usd_per_1m": 10
    },
    {
      "id": "openai-o3",
      "provider": "OpenAI",
      "model": "OpenAI o3",
      "context_window": 200000,
      "input_usd_per_1m": 2,
      "cached_input_usd_per_1m": 0.5,
      "output_usd_per_1m": 8
    },
    {
      "id": "deepseek-v3-2",
      "provider": "DeepSeek",
      "model": "DeepSeek V3.2",
      "context_window": 128000,
      "input_usd_per_1m": 0.27,
      "cached_input_usd_per_1m": 0.07,
      "output_usd_per_1m": 1.1
    },
    {
      "id": "gemini-2-5-flash",
      "provider": "Google",
      "model": "Gemini 2.5 Flash",
      "context_window": 1048576,
      "input_usd_per_1m": 0.3,
      "cached_input_usd_per_1m": 0.075,
      "output_usd_per_1m": 2.5
    }
  ]
}