# Claude Opus 5.5

> Anthropic's model for long-running agentic coding and knowledge work, with adaptive thinking that is always on.

## Key facts

- Model author: Anthropic
- Input: $4.00 per 1M tokens
- Output: $20.00 per 1M tokens
- Cached input: $0.20 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
- Released: 2026-09-22
- Knowledge cutoff: Jun 2026
- Model IDs: `anthropic/claude-opus-5-5`, `jd/claude-opus-5-5`
- Model page: https://www.realrelay.ai/model/anthropic/claude-opus-5-5

## Overview

Claude Opus 5.5 is a model from Anthropic designed for long-running agentic coding and knowledge work. Adaptive thinking is always on, so the model decides how much to reason as a task unfolds. It supports tool calling and image input, and its 1M-token context window keeps a large codebase or document set in view.

Claude Opus 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. It was released on September 22, 2026. Its knowledge cutoff is June 2026.

## Capabilities

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

Always-on adaptive thinking suits long runs where difficulty changes from step to step. Tool calling lets Claude Opus 5.5 act on a repository or workspace, and image input lets it work from screenshots and charts.

## Pricing

Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens. Cache reads are $0.20 per 1M tokens.

Claude Opus 5.5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Opus 5.5 for long-running agentic coding, such as an agent that migrates a service across many files, runs tests through tool calls and keeps working until the change is complete.

It also fits knowledge work that spans many sources: reading long documents and screenshots, comparing them and writing a structured report in one 1M-token session.

## 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-opus-5-5", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Claude Opus 5.5?

Claude Opus 5.5 is a model from Anthropic designed for long-running agentic coding and knowledge work. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Opus 5.5 cost?

Claude Opus 5.5 costs $4.00 per 1M input tokens and $20.00 per 1M output tokens, with cache reads at $0.20 per 1M tokens.

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

Claude Opus 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 Opus 5.5 support?

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

### Does Claude Opus 5.5 support tool calling?

Yes. Claude Opus 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.

### When was Claude Opus 5.5 released?

Claude Opus 5.5 was released on September 22, 2026. Its knowledge cutoff is June 2026.

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

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