# Claude Opus 4.8

> A generally available Anthropic Opus-family model for demanding reasoning and coding, with a 1M-token context window.

## 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: 2026-05-27
- Knowledge cutoff: Jan 2026
- Model IDs: `anthropic/claude-opus-4-8`, `jd/claude-opus-4-8`
- Model page: https://www.realrelay.ai/model/anthropic/claude-opus-4-8

## Overview

Claude Opus 4.8 is a generally available model from Anthropic's Opus family, built for demanding reasoning and coding work. It supports reasoning, tool calling and image input alongside text, and returns text. The 1M-token context window lets it hold large codebases, long documents and extended conversations in a single request.

Claude Opus 4.8 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 May 27, 2026. Its knowledge cutoff is January 2026.

## Capabilities

Claude Opus 4.8 supports reasoning, tool calling and image understanding. It accepts text and image as input and produces text as output.

Reasoning and tool calling work together so Claude Opus 4.8 can plan multi-step tasks and act on external systems, while image input allows it to interpret screenshots and charts that accompany a question.

## Pricing

Claude Opus 4.8 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 4.8 is available through RealRelay's OpenAI-compatible API.

## Use cases

Use Claude Opus 4.8 for demanding coding work, such as reading a large codebase, planning a change across files and calling tools to run tests, with the 1M-token window holding the code and its history.

It also handles demanding reasoning over long inputs: contracts, research papers or reports supplied with figures and screenshots, answered with a written analysis.

## 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-4-8", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is Claude Opus 4.8?

Claude Opus 4.8 is a generally available model from Anthropic's Opus family, built for demanding reasoning and coding work. It supports reasoning, tool calling and image understanding and accepts text and image input.

### How much does Claude Opus 4.8 cost?

Claude Opus 4.8 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 4.8?

Claude Opus 4.8 has a 1M-token context window and can generate up to 128K tokens in a single response.

### What inputs and outputs does Claude Opus 4.8 support?

Claude Opus 4.8 accepts text and image input and returns text output.

### Does Claude Opus 4.8 support tool calling?

Yes. Claude Opus 4.8 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 4.8 released?

Claude Opus 4.8 was released on May 27, 2026. Its knowledge cutoff is January 2026.

### How do I call Claude Opus 4.8 via the API?

Call Claude Opus 4.8 through RealRelay's OpenAI-compatible API using the model ID anthropic/claude-opus-4-8.