# Claude Haiku 5.5

> Anthropic's model for high-volume, latency-sensitive work such as classification, extraction and routing.

## Key facts

- Model author: Anthropic
- Input: $0.10 per 1M tokens (starting tier)
- Output: $0.50 per 1M tokens (starting tier)
- Cached input: $0.01 per 1M tokens
- Context window: 1,000,000 tokens
- Maximum output: 128,000 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: reasoning, tools, vision
- Knowledge cutoff: Jun 2026
- Model IDs: `anthropic/claude-haiku-5-5`
- Model page: https://www.realrelay.ai/model/anthropic/claude-haiku-5-5

## Overview

Claude Haiku 5.5 is a model from Anthropic designed for high-volume, latency-sensitive tasks such as classification, extraction and routing. It uses adaptive thinking, supports tool calling and image input, and has a 1M-token context window, so it can handle large inputs while keeping responses quick.

Claude Haiku 5.5 has a 1M-token context window and can generate up to 128K output tokens. It accepts text and image input and returns text output. Its knowledge cutoff is June 2026.

## Capabilities

Claude Haiku 5.5 supports reasoning, tool calling and image understanding. It accepts text and image as input and produces text as output.

Adaptive thinking lets the model decide how much to reason, which helps when some requests are simple and others need more thought. Tool calling lets it trigger functions, and image input lets it classify or extract information from screenshots and scanned pages.

## Pricing

Claude Haiku 5.5 starts from $0.10 per 1M input tokens and from $0.50 per 1M output tokens. Cache reads start from $0.01 per 1M tokens.

Pricing is dynamic, so the prices shown are starting prices. Claude Haiku 5.5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Haiku 5.5 as a classifier or router: it can label incoming tickets, messages or documents, or decide which downstream tool should handle a request, at high volume and low latency.

It also suits extraction, turning invoices, forms or screenshots into structured fields, with the 1M-token window available for long source documents.

## 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": "anthropic/claude-haiku-5-5", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Claude Haiku 5.5?

Claude Haiku 5.5 is a model from Anthropic designed for high-volume, latency-sensitive tasks such as classification, extraction and routing. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Haiku 5.5 cost?

Claude Haiku 5.5 starts from $0.10 per 1M input tokens and from $0.50 per 1M output tokens, with cache reads from $0.01 per 1M tokens. Pricing is dynamic, so these are starting prices.

### What is the context window of Claude Haiku 5.5?

Claude Haiku 5.5 has a 1M-token context window and can generate up to 128K tokens in a single response.

### What inputs and outputs does Claude Haiku 5.5 support?

Claude Haiku 5.5 accepts text and image input and returns text output.

### Does Claude Haiku 5.5 support tool calling?

Yes. Claude Haiku 5.5 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.

### How do I call Claude Haiku 5.5 via the API?

Call Claude Haiku 5.5 through RealRelay's OpenAI-compatible API using the model ID anthropic/claude-haiku-5-5.