# Claude Haiku 4.5

> Anthropic's efficient, low-latency model with near-frontier intelligence, reasoning, tool calling and image input.

## Key facts

- Model author: Anthropic
- Input: $1.00 per 1M tokens
- Output: $5.00 per 1M tokens
- Cached input: $0.10 per 1M tokens
- Context window: 200,000 tokens
- Maximum output: 64,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, tools, vision
- Released: 2025-10-01
- Knowledge cutoff: Feb 2025
- Model IDs: `jd/claude-haiku-4-5`
- Model page: https://www.realrelay.ai/model/anthropic/claude-haiku-4-5

## Overview

Claude Haiku 4.5 is a model from Anthropic that pairs near-frontier intelligence with low latency and efficiency. It is aimed at applications where fast responses matter, and it supports reasoning, tool calling and image input. It accepts text and image input and returns text.

Claude Haiku 4.5 has a 200K-token context window and can generate up to 64K output tokens. It accepts text and image input and returns text output. It was released on October 1, 2025. Its knowledge cutoff is February 2025.

## Capabilities

Claude Haiku 4.5 supports reasoning, tool calling and image understanding. It accepts text and image as input and produces text as output.

Reasoning and tool calling make it usable in agent loops where every step needs a quick answer, and image input lets it read screenshots and photos in the same request.

## Pricing

Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens. Cache reads are $0.10 per 1M tokens.

Claude Haiku 4.5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Haiku 4.5 for high-throughput assistants that need quick replies, such as a support chat that reads a customer screenshot and answers promptly.

It also fits agent workflows made of many small tool calls, where low latency per step keeps the whole run responsive, and summaries of long inputs that fit the 200K-token window.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "jd/claude-haiku-4-5", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Claude Haiku 4.5?

Claude Haiku 4.5 is a model from Anthropic that pairs near-frontier intelligence with low latency and efficiency. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Haiku 4.5 cost?

Claude Haiku 4.5 costs $1.00 per 1M input tokens and $5.00 per 1M output tokens, with cache reads at $0.10 per 1M tokens.

### What is the context window of Claude Haiku 4.5?

Claude Haiku 4.5 has a 200K-token context window and can generate up to 64K tokens in a single response.

### What inputs and outputs does Claude Haiku 4.5 support?

Claude Haiku 4.5 accepts text and image input and returns text output.

### Does Claude Haiku 4.5 support tool calling?

Yes. Claude Haiku 4.5 supports tool calling, so it can call functions you define and use the results in multi-step tasks. It also supports reasoning and image understanding.

### When was Claude Haiku 4.5 released?

Claude Haiku 4.5 was released on October 1, 2025. Its knowledge cutoff is February 2025.

### How do I call Claude Haiku 4.5 via the API?

Call Claude Haiku 4.5 through RealRelay's OpenAI-compatible API using the model ID jd/claude-haiku-4-5.