ClaudeStore/Docs
⚠ These docs are a work in progress. Some content may be inaccurate or temporarily AI-generated.

Pricing

Claude API pricing — cost per token for Opus, Sonnet, and Haiku. Credit-based billing, no monthly fees, pay as you go.

Pricing model: Pay-as-you-go credits. Starter: $5 / 1k credits. Pro: $50 / 10k credits. Business: $500 / 105k credits.

Billing Model

Claude Code API uses credit-based billing. You are charged based on actual token consumption per request, with public request pricing set about 30% below Anthropic's official token rates.

Cost Formula

Request cost calculationtext
cost = (input_tokens × input_rate)
 + (output_tokens × output_rate)
 + (cache_write_tokens × cache_write_rate)
 + (cache_read_tokens × cache_read_rate)

Token Categories

CategoryDescription
Input (uncached)Standard input tokens not served from cache
OutputGenerated response tokens
Cache WriteTokens written to the prompt cache on first request
Cache ReadTokens served from prompt cache on subsequent requests

Per-Model Rates

Rates are per million tokens (MTok). These are the public rates used for request deductions. Use GET /v1/models/info for live rates.

ModelInputOutputCache WriteCache Read
claude-opus-4.6$3.50$17.50$4.375$0.35
claude-opus-4.7$3.50$17.50$4.375$0.35
claude-sonnet-4.6$2.10$10.50$2.625$0.21
claude-haiku-4.5$0.70$3.50$0.875$0.07

Important Notes

  • Streaming requests are billed the same as non-streaming requests
  • Cache read tokens are significantly cheaper than uncached input tokens
  • Each model has its own rate table — use GET /v1/models/info for current rates
Use the /v1/models/info endpoint to get current per-model pricing rates programmatically.

Ready to start?

Get API access to all Claude models in under 2 minutes.

View Plans