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
| Category | Description |
|---|---|
| Input (uncached) | Standard input tokens not served from cache |
| Output | Generated response tokens |
| Cache Write | Tokens written to the prompt cache on first request |
| Cache Read | Tokens 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.
| Model | Input | Output | Cache Write | Cache 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/infofor current rates
Use the
/v1/models/info endpoint to get current per-model pricing rates programmatically.