API Pricing

LLM token prices across providers, as an API.

$X / month

Subscribe

Already subscribed? Sign in to get your API key.

What you get

  • Input, cached input, and output prices per 1M tokens for every provider serving a model
  • Prices refreshed from provider pricing pages
  • Cache parity: how far an uncached prompt must shrink to match a cached price
  • Tool definitions so an LLM agent can call the API directly

Endpoints

GET /prices.tsv?model=MODEL
GET /models/MODEL/providers
GET /models/MODEL/cache-parity?tokens=N
GET /tools

Example

curl -H "Authorization: Bearer YOUR_KEY" \
  https://api.aipricingapi.com/models/llama-3.3-70b-instruct/providers