Key Capabilities
- OpenAI-compatible — Drop-in replacement for the OpenAI SDK, no other code changes needed
- Ultra-fast response — Optimized for low latency
- Cost-effective — Far lower per-token cost than larger models
- Streaming — Real-time token streaming via SSE
- Capable — Excellent performance on coding, writing, and analysis tasks
Quick Example
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Fixed value: claude-haiku-4-5 |
messages | array | Yes | Array of { role, content } objects |
max_tokens | integer | No | Maximum number of tokens to generate |
temperature | float | No | 0–2, controls randomness, default 1 |
stream | boolean | No | Enable SSE streaming, default false |
top_p | float | No | Nucleus sampling threshold, default 1 |
stop | string / array | No | Sequences where generation stops |
API Reference
View the interactive API Playground for Claude Haiku 4.5.

