Key capabilities
- OpenAI-compatible — Works as a drop-in replacement with the OpenAI SDK
- 1M context window — 128K max output tokens
- Adaptive thinking — Smart reasoning that triggers only when the task needs it
- Fast mode — Up to 2.5x higher output speed at premium pricing (research preview)
- Mid-conversation system messages — Append updated instructions without restating the full system prompt
- Lower cache minimum — 1,024 token minimum cacheable prompt length
- Streaming — Supports real-time token streaming via SSE
Quick example
Parameters
Claude Opus 4.8 does not support custom sampling values. Omit
temperature, top_p, and top_k for normal requests. For backward compatibility, temperature: 1 and top_p values from 0.99 to 1 are accepted; any top_k value or other sampling value returns a 400 error. Use prompting to guide model behavior. See Anthropic’s API parameter deprecations.API Reference
View the interactive API playground for Claude Opus 4.8.