# Claude Haiku 4.5

Fastest model with near-frontier intelligence. Best cost-performance ratio.

## Overview

- **Provider:** Anthropic
- **Model ID:** `claude-haiku-4-5`
- **Type:** Chat
- **Canonical URL:** https://modelstack.cc/models/chat/claude-haiku-4-5
- **Version:** Haiku 4.5
- **Best for:** High-volume tasks, low-latency chat, sub-agent orchestration, rapid prototyping

## Pricing

| Usage | Price |
| --- | ---: |
| Input | $1 / 1M tokens |
| Output | $5 / 1M tokens |
| Cache read | $0.1 / 1M tokens |
| Cache write (5 minutes) | $1.25 / 1M tokens |
| Cache write (1 hour) | $2 / 1M tokens |

## Specifications

- **Context window:** 200K
- **Maximum output:** 64K
- **Typical latency:** 8 ms
- **Released:** 2025-10

## Capabilities

- chat
- tool_use
- reasoning
- vision
- coding
- analysis
- long_context

## API usage

Use this model ID in a ModelStack API request:

```json
{
  "model": "claude-haiku-4-5"
}
```

For the rendered page, visit https://modelstack.cc/models/chat/claude-haiku-4-5.