LLM Pricing API

One free GET request returns 32 model prices — input, output, cache and batch rates for OpenAI, Anthropic, Google and DeepSeek models, JSON-formatted and machine-ready. Updated 2026-09-24.

Endpoint

GET https://llmprices.org/api/v1/prices

Example Response

curl https://llmprices.org/api/v1/prices

{
  "source": "llmprices.org",
  "license": "CC BY 4.0 — attribute llmprices.org with a link",
  "updated": "2026-09-24",
  "count": 32,
  "models": [
    {
      "name": "GPT-6 Sol",
      "api_id": "gpt-6-sol",
      "vendor": "OpenAI",
      "input": 2.0,
      "output": 10.0,
      "cache": 0.2,
      "batch_input": 1.0,
      "batch_output": 5.0,
      ...
    }
  ]
}

Fields

FieldMeaning
input / outputStandard tier price per 1M tokens (USD)
cacheGemini/OpenAI/DeepSeek: cached-input read price; Claude: 5-min cache write price
batch_input / batch_outputBatch API rate (50% discount where offered)
price_change_date / *_afterAnnounced future price change (e.g. Gemini 3.x doubles on 2027-01-01)

Terms

Free to use, including commercial projects, under CC BY 4.0 — attribute llmprices.org with a link. Data is sourced from official provider pricing pages; verify critical decisions against the provider before purchase. Fair-use rate limit applies.

Frequently Asked Questions

Is the LLM pricing API free?

Yes — free including commercial use, with attribution (CC BY 4.0).

How often is the data updated?

Provider pricing pages are monitored daily; changes are applied automatically.

Which providers are covered?

OpenAI, Anthropic, Google and DeepSeek — 32 models and growing. Hosted prices (Qwen, Llama via cloud partners) are on the roadmap.

Do I need an API key?

No key required for the JSON endpoint.

See Also