Claude Opus 5.5 API Documentation - MixRoute

Claude Opus model for long-running agentic coding and knowledge work.

Model Information

Field	Description
`model`	claude-opus-5-5
`context`	1M tokens
`max output`	128K tokens
`endpoint`	POST /v1/messages

Context and output sizes describe the model specification. Effective request limits, availability, and billing depend on the MixRoute route.

Capabilities and Usage

Accepts text and images; returns text and tool-use content blocks.
Adaptive thinking is always on. Set output_config.effort to low, medium (default), high, xhigh, or max. Do not send thinking.type=enabled, thinking.type=disabled, or legacy budget_tokens settings.
tool_choice supports auto (default) and none. Forced choices any and tool are rejected; use auto for tool workflows.

Request Example

Set MIXROUTE_API_KEY before making the request.

curl --request POST "https://api.mixroute.ai/v1/messages" \
  --header "Authorization: Bearer $MIXROUTE_API_KEY" \
  --header "Content-Type: application/json" \
  --header "anthropic-version: 2023-06-01" \
  --data '{
  "model": "claude-opus-5-5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Explain the tradeoffs of database indexes."
    }
  ]
}'

Request Fields

Field	Description
`model`	Required. Use the exact model ID above.
`messages`	Required conversation messages with role and content.
`max_tokens`	Required output-token budget.
`output_config.effort`	Optional. `low`, `medium`, `high`, `xhigh`, or `max`; default: `medium`.
`tool_choice`	Optional object. Use `{"type":"auto"}` or `{"type":"none"}`; `any` and `tool` are not supported.

Complete request format: messages.