# Claude Opus 5

> Anthropic's flagship model for demanding reasoning, coding and long-horizon agentic work, including code review and bug finding.

## 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: 2026-07-24
- Knowledge cutoff: May 2026
- Model IDs: `anthropic/claude-opus-5`, `jd/claude-opus-5`
- Model page: https://www.realrelay.ai/model/anthropic/claude-opus-5

## Overview

Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding and long-horizon agentic work. Anthropic highlights end-to-end software tasks, code review and bug finding, and visual analysis. It supports reasoning, tool calling and image input, with a 1M-token context window for large codebases.

Claude Opus 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 July 24, 2026. Its knowledge cutoff is May 2026.

## Capabilities

Claude Opus 5 supports reasoning, tool calling and image understanding. It accepts text and image as input and produces text as output.

Visual analysis comes from image input, so Claude Opus 5 can inspect screenshots, diagrams and charts alongside code. Reasoning and tool calling let it find bugs, review changes and run checks as part of a longer agent task.

## Pricing

Claude Opus 5 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 5 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Opus 5 for end-to-end software tasks: reading a repository, implementing a change, calling tools to run tests and reviewing the result, within the 1M-token context window.

It is also suited to code review and bug finding, and to visual analysis tasks where a screenshot, chart or diagram must be interpreted together with text.

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

## FAQ

### What is Claude Opus 5?

Claude Opus 5 is Anthropic's flagship model for demanding reasoning, coding and long-horizon agentic work. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Opus 5 cost?

Claude Opus 5 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 5?

Claude Opus 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 support?

Claude Opus 5 accepts text and image input and returns text output.

### Does Claude Opus 5 support tool calling?

Yes. Claude Opus 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 released?

Claude Opus 5 was released on July 24, 2026. Its knowledge cutoff is May 2026.

### How do I call Claude Opus 5 via the API?

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