> ## Documentation Index
> Fetch the complete documentation index at: https://mixroute.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.
# Claude Haiku 5.5
> Low-latency Claude model for classification, routing, extraction, and subagent tasks.
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.
```bash theme={null}
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](/docs/api-reference/endpoint/messages).
This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.