Anthropic: claude-opus-5-5
Claude Opus 5.5 is Anthropic's flagship model in the Claude 5.5 generation. On the Artificial Analysis Intelligence Index it ranks #1 of 352 models, making it the highest-scoring model on that leaderboard. The model supports adjustable reasoning effort, and its index score scales with that setting: 42.3 at low effort, 51.2 at medium, 53.6 at high, 56.0 at xhigh, and 57.6 at max. Because it sits at the top of the Intelligence Index, Claude Opus 5.5 is best suited to demanding reasoning work where answer quality matters more than speed or cost — for example complex analysis, multi-step problem solving, and tasks that benefit from extended deliberation. Lower reasoning effort settings offer a way to trade some of that depth for faster responses on simpler requests. On the Artificial Analysis Intelligence Index leaderboard, Claude Opus 5.5 is listed above Claude Sonnet 5.5, Kimi K3.1 Pro, Claude Fable 5.1, Qwen3.8 Max, GPT-6 Astra, Gemini 4 Argon (High), GPT-6.1 Sol, and Claude Opus 5.
Inputs used for the providers' own purposes
At least one provider of this model uses your inputs for its own purposes, for example to train AI models. Do not enter personal data of third parties or sensitive data. You can object to this use at any time in your account settings or via "Manage consents" in the chat.
Read the privacy policyPricing
Uptime
Performance
Usage & Ranking
Supported parameters
All providers = every upstream serving this model supports it. Some providers = depends on which upstream handles the request. Default = the value sent when you leave the parameter unset.
| Parameter | Providers | Default |
|---|---|---|
| include_reasoning | Some providers | - |
| max_completion_tokens | Some providers | - |
| max_tokens | Some providers | - |
| reasoning | Some providers | - |
| reasoning_effort | Some providers | - |
| response_format | Some providers | - |
| stop | Some providers | - |
| structured_outputs | Some providers | - |
| tool_choice | Some providers | - |
| tools | Some providers | - |
| verbosity | Some providers | - |