claude-haiku-4-5
Claude Haiku 4.5 is Anthropic’s fastest and most efficient model, delivering near-frontier intelligence at a fraction of the cost and latency of larger Claude models. Matching Claude Sonnet 4’s performance across reasoning, coding, and computer-use tasks, Haiku 4.5 brings frontier-level capability to real-time and high-volume applications. It introduces extended thinking to the Haiku line; enabling controllable reasoning depth, summarized or interleaved thought output, and tool-assisted workflows with full support for coding, bash, web search, and computer-use tools. Scoring \u003E73% on SWE-bench Verified, Haiku 4.5 ranks among the world’s best coding models while maintaining exceptional responsiveness for sub-agents, parallelized execution, and scaled deployment.
Input
Output
Anthropic Claude 4.5 Haiku Documentation
Claude 4.5 Haiku brings frontier-level intelligence to high-volume, sub-second response applications. Scoring >73% on SWE-bench Verified, it ranks as a world-class coding model that introduces extended thinking capabilities to a lightweight, highly parallelizable model architecture.
Key Capabilities
- Sub-Second Responsiveness: Optimized for high-throughput, low-latency loops, making it ideal for real-time user interactions and sub-agents.
- Extended Thinking: Supports native reasoning depth control, allowing developers to choose between summarized or interleaved chain-of-thought outputs.
- Elite Coding Prowess: Exceptional performance on SWE-bench Verified, making it highly reliable for automated bug-fixing, code reviews, and unit test generation.
- Tool-Assisted Workflows: Native, robust support for executing function calls, interacting with Bash environments, performing web searches, and handling computer-use tools.
- Massive Scalability: The cost-to-performance champion for running large clusters of parallelized agentic workers simultaneously.
Request Parameters
To interact with this model via an OpenAI-compatible gateway or OpenRouter endpoint:
| Parameter | Type | Required | Description |
|---|---|---|---|
model |
string |
Yes | Use "claude-haiku-4-5" or "anthropic/claude-4.5-haiku". |
messages |
array |
Yes | Array of standard conversation objects (role/content). |
max_tokens |
integer |
No | Limits generation length. Default: 4096. |
temperature |
float |
No | Recommended: 0.0 for deterministic parsing/coding; 0.6 for chat. |
extra_body |
object |
No | Used to configure extended thinking/reasoning parameters. |
Unlock the most affordable AI hosting
Run models at scale with our fully managed GPU infrastructure, delivering enterprise-grade uptime at the industry's best rates.