Claude Haiku 5.5 API Documentation - MixRoute

Low-latency Claude model for classification, routing, extraction, and subagent tasks.

Model Information

Field	Description
`model`	claude-haiku-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 enabled by default. Configure reasoning effort with output_config.effort; the default is medium.
Omit temperature, top_p, and top_k.

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-haiku-5-5",
  "max_tokens": 1024,
  "messages": [
    {
      "role": "user",
      "content": "Summarize the benefits of database indexes."
    }
  ]
}'

Request Fields

Field	Description
`model`	Required. Use `claude-haiku-5-5`.
`messages`	Required conversation messages with role and content.
`max_tokens`	Required output-token budget.

Complete request format: Messages API.