# Claude Opus 4.7

> Anthropic's model for long-running, asynchronous agents, covering coding and agentic work with reasoning and tool calling.

## Key facts

- Model author: Anthropic
- Input: $4.8404 per 1M tokens (starting price)
- Output: $24.2017 per 1M tokens (starting price)
- Cached input: $0.484 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: 2026-04-16
- Knowledge cutoff: Jan 2026
- Model IDs: `anthropic/claude-opus-4-7`, `jd/claude-opus-4-7`
- Model page: https://www.realrelay.ai/model/anthropic/claude-opus-4-7

## Overview

Claude Opus 4.7 is a model from Anthropic built for long-running, asynchronous agents. It is aimed at coding and agentic work that continues over many steps without a person watching each one. It supports reasoning, tool calling and image input, with a 1M-token context window.

Claude Opus 4.7 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 April 16, 2026. Its knowledge cutoff is January 2026.

## Capabilities

Claude Opus 4.7 supports reasoning, tool calling and image understanding. It accepts text and image as input and produces text as output.

Asynchronous agents depend on reliable tool use, so Claude Opus 4.7 pairs tool calling with reasoning, letting an agent plan, act and check results across a long task. Image input adds screenshots and diagrams to the context.

## Pricing

Claude Opus 4.7 starts from $4.84 per 1M input tokens and from $24.20 per 1M output tokens. Cache reads start from $0.484 per 1M tokens.

Pricing is tiered, and the price shown is the starting tier. Claude Opus 4.7 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Opus 4.7 for background coding agents that pick up a task, work through a repository, call tools to build and test, and continue across many steps using the 1M-token window.

It also suits long-running agentic jobs outside code, such as reviewing a large set of documents and screenshots in sequence and compiling the findings.

## 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-4-7", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Claude Opus 4.7?

Claude Opus 4.7 is a model from Anthropic built for long-running, asynchronous agents. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Opus 4.7 cost?

Claude Opus 4.7 starts from $4.84 per 1M input tokens and from $24.20 per 1M output tokens, with cache reads from $0.484 per 1M tokens. Pricing is tiered, and these are the starting-tier prices.

### What is the context window of Claude Opus 4.7?

Claude Opus 4.7 has a 1M-token context window and can generate up to 128K tokens in a single response.

### What inputs and outputs does Claude Opus 4.7 support?

Claude Opus 4.7 accepts text and image input and returns text output.

### Does Claude Opus 4.7 support tool calling?

Yes. Claude Opus 4.7 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 4.7 released?

Claude Opus 4.7 was released on April 16, 2026. Its knowledge cutoff is January 2026.

### How do I call Claude Opus 4.7 via the API?

Call Claude Opus 4.7 through RealRelay's OpenAI-compatible API using the model ID anthropic/claude-opus-4-7.