Skip to content
MyStackPlan
LLM APIs & Inference

Anthropic Claude API pricing

The Claude models by API, billed per token, with discounts for prompt caching and batch requests.

Try it in the builderOfficial pricing pageReport a wrong price

Every plan below was checked against Anthropic Claude API's own pages on . Prices in USD.

Plans

Pay as you go

Pay as you go

At the limit
Bills for extra usage
  • Billed per million tokens, with input and output priced separately.
  • Prompt caching reads cost a fraction of the input price, and the Batch API halves both input and output prices.
  • Claude 4.7 and later models use a newer tokenizer that produces about 30% more tokens for the same text.
  • US-only inference adds 10% on Claude 4.6 and later models.

Source: platform.claude.com · checked

Models

ModelInput per 1M tokensOutput per 1M tokensAnnounced change
Claude Haiku 5.5For prompts up to 100,000 tokens; longer prompts cost $0.50 in and $2.50 out$0.10$0.50None announced
Claude Sonnet 5.5$2.00$10.00None announced
Claude Opus 5.5$4.00$20.00None announced

Works well with

  • Cloudflare AI GatewayCloudflare AI Gateway can sit in front of Anthropic requests to add logging, caching and rate limits.
  • OpenRouterOpenRouter lets you call Anthropic models through one API.
  • Vercel AI GatewayVercel AI Gateway lets you call Anthropic models through one gateway.

Alternatives for llm apis & inference