anthropic/claude-sonnet-4
Claude Sonnet 4 significantly enhances the capabilities of its predecessor, Sonnet 3.7, excelling in both coding and reasoning tasks with improved precision and controllability. Achieving state-of-the-art performance on SWE-bench (72.7%),...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| $3.00 | $15.00 | 1M | 100% | |
| Amazon Bedrock | $3.00 | $15.00 | 200K | — |
| Amazon Bedrock | $3.00 | $15.00 | 200K | 99.9% |
| $3.00 | $15.00 | 1M | — | |
| $3.00 | $15.00 | 1M | — |
Claude Sonnet 4 costs $3.00 per million input tokens and $15.00 per million output tokens via OpenRouter, making it 267th cheapest of 298 paid models.
Claude Sonnet 4 scores 33.0 on the Artificial Analysis Intelligence Index, ranking 66th of 180 benchmarked models, with a GPQA Diamond score of 68%.
Claude Sonnet 4 generates around 41 tokens per second with 658ms time-to-first-token (p50), the 201st fastest tracked model.
Claude Sonnet 4 supports a 1M-token context window and can output up to 64K tokens. It accepts image, text, file input.