{
  "updated_at": "2026-08-18",
  "methodology": "https://harpd.com/methodology/model-pricing/",
  "description": "Public list prices per 1,000,000 tokens in USD, sourced from official provider pricing pages. For comparison and research only — not a quote.",
  "currency": "USD",
  "unit": "per_million_tokens",
  "models": [
    {
      "id": "claude-opus-4-8",
      "provider": "Anthropic",
      "model": "Claude Opus 4.8",
      "input_per_million": 5,
      "cached_input_per_million": 0.5,
      "output_per_million": 25,
      "batch_discount": 0.5,
      "context_window": 200000,
      "status": "available",
      "effective_at": "2026-06-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.anthropic.com/en/docs/about-claude/pricing",
      "note": null
    },
    {
      "id": "claude-sonnet-5",
      "provider": "Anthropic",
      "model": "Claude Sonnet 5",
      "input_per_million": 2,
      "cached_input_per_million": 0.2,
      "output_per_million": 10,
      "batch_discount": 0.5,
      "context_window": 200000,
      "status": "available",
      "effective_at": "2026-08-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.anthropic.com/en/docs/about-claude/pricing",
      "note": "Introductory pricing ($2/$10) runs through 2026-08-31; standard $3/$15 applies from 2026-09-01."
    },
    {
      "id": "claude-sonnet-4-5",
      "provider": "Anthropic",
      "model": "Claude Sonnet 4.5",
      "input_per_million": 3,
      "cached_input_per_million": 0.3,
      "output_per_million": 15,
      "batch_discount": 0.5,
      "context_window": 200000,
      "status": "available",
      "effective_at": "2026-03-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.anthropic.com/en/docs/about-claude/pricing",
      "note": null
    },
    {
      "id": "claude-haiku-4-5",
      "provider": "Anthropic",
      "model": "Claude Haiku 4.5",
      "input_per_million": 1,
      "cached_input_per_million": 0.1,
      "output_per_million": 5,
      "batch_discount": 0.5,
      "context_window": 200000,
      "status": "available",
      "effective_at": "2026-03-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.anthropic.com/en/docs/about-claude/pricing",
      "note": null
    },
    {
      "id": "gpt-5",
      "provider": "OpenAI",
      "model": "GPT-5",
      "input_per_million": 1.25,
      "cached_input_per_million": 0.125,
      "output_per_million": 10,
      "batch_discount": 0.5,
      "context_window": 400000,
      "status": "available",
      "effective_at": "2026-06-01",
      "verified_at": "2026-08-18",
      "source": "https://openai.com/api/pricing/",
      "note": null
    },
    {
      "id": "gpt-5-mini",
      "provider": "OpenAI",
      "model": "GPT-5 mini",
      "input_per_million": 0.25,
      "cached_input_per_million": 0.025,
      "output_per_million": 2,
      "batch_discount": 0.5,
      "context_window": 400000,
      "status": "available",
      "effective_at": "2026-06-01",
      "verified_at": "2026-08-18",
      "source": "https://openai.com/api/pricing/",
      "note": null
    },
    {
      "id": "gpt-5-nano",
      "provider": "OpenAI",
      "model": "GPT-5 nano",
      "input_per_million": 0.05,
      "cached_input_per_million": 0.005,
      "output_per_million": 0.4,
      "batch_discount": 0.5,
      "context_window": 400000,
      "status": "available",
      "effective_at": "2026-06-01",
      "verified_at": "2026-08-18",
      "source": "https://openai.com/api/pricing/",
      "note": null
    },
    {
      "id": "gpt-4-1",
      "provider": "OpenAI",
      "model": "GPT-4.1",
      "input_per_million": 2,
      "cached_input_per_million": 0.2,
      "output_per_million": 8,
      "batch_discount": 0.5,
      "context_window": 1000000,
      "status": "available",
      "effective_at": "2025-04-14",
      "verified_at": "2026-08-18",
      "source": "https://openai.com/api/pricing/",
      "note": null
    },
    {
      "id": "gemini-2-5-pro",
      "provider": "Google",
      "model": "Gemini 2.5 Pro",
      "input_per_million": 1.25,
      "cached_input_per_million": 0.125,
      "output_per_million": 10,
      "batch_discount": 0.5,
      "context_window": 1000000,
      "status": "available",
      "effective_at": "2025-03-25",
      "verified_at": "2026-08-18",
      "source": "https://ai.google.dev/gemini-api/docs/pricing",
      "note": "Prompts over 200k tokens bill at $2.50 input / $15 output. Context caching ~$0.125/1M for ≤200k."
    },
    {
      "id": "gemini-2-5-flash",
      "provider": "Google",
      "model": "Gemini 2.5 Flash",
      "input_per_million": 0.3,
      "cached_input_per_million": 0.075,
      "output_per_million": 2.5,
      "batch_discount": 0.5,
      "context_window": 1000000,
      "status": "available",
      "effective_at": "2025-03-25",
      "verified_at": "2026-08-18",
      "source": "https://ai.google.dev/gemini-api/docs/pricing",
      "note": null
    },
    {
      "id": "gemini-2-5-flash-lite",
      "provider": "Google",
      "model": "Gemini 2.5 Flash-Lite",
      "input_per_million": 0.1,
      "cached_input_per_million": null,
      "output_per_million": 0.4,
      "batch_discount": 0.5,
      "context_window": 1000000,
      "status": "available",
      "effective_at": "2025-03-25",
      "verified_at": "2026-08-18",
      "source": "https://ai.google.dev/gemini-api/docs/pricing",
      "note": null
    },
    {
      "id": "mistral-large-3",
      "provider": "Mistral",
      "model": "Mistral Large 3",
      "input_per_million": 2,
      "cached_input_per_million": null,
      "output_per_million": 6,
      "batch_discount": 0.5,
      "context_window": 128000,
      "status": "available",
      "effective_at": "2026-01-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.mistral.ai/cloud/cloud-pricing/",
      "note": null
    },
    {
      "id": "mistral-small-3-1",
      "provider": "Mistral",
      "model": "Mistral Small 3.1",
      "input_per_million": 0.1,
      "cached_input_per_million": null,
      "output_per_million": 0.3,
      "batch_discount": 0.5,
      "context_window": 128000,
      "status": "available",
      "effective_at": "2026-01-01",
      "verified_at": "2026-08-18",
      "source": "https://docs.mistral.ai/cloud/cloud-pricing/",
      "note": null
    },
    {
      "id": "deepseek-v3",
      "provider": "DeepSeek",
      "model": "DeepSeek V3",
      "input_per_million": 0.27,
      "cached_input_per_million": null,
      "output_per_million": 1.1,
      "batch_discount": null,
      "context_window": 128000,
      "status": "available",
      "effective_at": "2025-12-26",
      "verified_at": "2026-08-18",
      "source": "https://api-docs.deepseek.com/quick_start/",
      "note": "DeepSeek moved to peak/off-peak pricing on 2026-08-17. Figures shown are approximate off-peak list rates — verify before budgeting."
    },
    {
      "id": "llama-3-1-70b",
      "provider": "Meta · Together",
      "model": "Llama 3.1 70B",
      "input_per_million": 0.88,
      "cached_input_per_million": null,
      "output_per_million": 0.88,
      "batch_discount": null,
      "context_window": 128000,
      "status": "available",
      "effective_at": "2024-07-23",
      "verified_at": "2026-08-18",
      "source": "https://www.together.ai/pricing",
      "note": "Resale price via Together AI."
    },
    {
      "id": "qwen-2-5-72b",
      "provider": "Alibaba · OpenRouter",
      "model": "Qwen 2.5 72B",
      "input_per_million": 0.4,
      "cached_input_per_million": null,
      "output_per_million": 0.4,
      "batch_discount": null,
      "context_window": 128000,
      "status": "available",
      "effective_at": "2024-09-19",
      "verified_at": "2026-08-18",
      "source": "https://openrouter.ai/models",
      "note": "Resale price via OpenRouter."
    }
  ]
}