anthropic/claude-sonnet-4.5
Claude Sonnet 4.5 is Anthropic’s most advanced Sonnet model to date, optimized for real-world agents and coding workflows. It delivers state-of-the-art performance on coding benchmarks such as SWE-bench Verified, with...
| Provider | In $/M | Out $/M | Context | Uptime |
|---|---|---|---|---|
| Amazon Bedrock | $3.00 | $15.00 | 1M | — |
| $3.00 | $15.00 | 1M | — | |
| Amazon Bedrock | $3.00 | $15.00 | 1M | 99.9% |
| Anthropic | $3.00 | $15.00 | 1M | 99.3% |
| $3.00 | $15.00 | 1M | 100% | |
| Amazon Bedrock | $3.00 | $15.00 | 1M | 99.5% |
| Anthropic | $3.00 | $15.00 | 1M | — |
Claude Sonnet 4.5 costs $3.00 per million input tokens and $15.00 per million output tokens via OpenRouter, making it 266th cheapest of 298 paid models.
Claude Sonnet 4.5 scores 37.1 on the Artificial Analysis Intelligence Index, ranking 58th of 179 benchmarked models, with a GPQA Diamond score of 73%.
Claude Sonnet 4.5 generates around 37 tokens per second with 884ms time-to-first-token (p50), the 218th fastest tracked model.
Claude Sonnet 4.5 supports a 1M-token context window and can output up to 64K tokens. It accepts text, image, file input.