# Claude Opus 4 API Pricing

As of October 10, 2026, Claude Opus 4 costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from GMI Cloud, the lowest of 4 providers. It has a 409,600-token context window and returns up to 32,000 tokens per response.

- Page: https://models.litellm.ai/models/claude-opus-4
- Lab: Anthropic
- LiteLLM model name: `gmi/anthropic/claude-opus-4`
- Context window: 409,600 tokens
- Max output: 32,000 tokens
- Added to LiteLLM: May 2025
- Prices updated: October 10, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| GMI Cloud | `gmi/anthropic/claude-opus-4` | $15.00 | $75.00 | – | – | – | 400K |
| Amazon Bedrock (snapshot 20250514) | `anthropic.claude-opus-4-20250514-v1:0` | $15.00 | $75.00 | $1.50 | – | – | 200K |
| Databricks | `databricks/databricks-claude-opus-4` | $15.00 | $75.00 | $1.50 | – | – | 200K |
| Vercel AI Gateway | `vercel_ai_gateway/anthropic/claude-opus-4` | $15.00 | $75.00 | $1.50 | – | – | 200K |
| Amazon Bedrock (EU cross-region, snapshot 20250514) | `eu.anthropic.claude-opus-4-20250514-v1:0` | $15.00 | $75.00 | $1.50 | – | – | 200K |
| Amazon Bedrock (US cross-region, snapshot 20250514) | `us.anthropic.claude-opus-4-20250514-v1:0` | $15.00 | $75.00 | $1.50 | – | – | 200K |

## Cost examples

1,000 requests with 2,000 input and 500 output tokens each:

- GMI Cloud: $67.50
- Amazon Bedrock: $67.50
- Vercel AI Gateway: $67.50
- Databricks: $67.50

100 long-document requests with 100,000 input and 2,000 output tokens each:

- GMI Cloud: $165.00
- Amazon Bedrock: $165.00
- Vercel AI Gateway: $165.00
- Databricks: $165.00

## Features

Supported: Function calling, Structured output, Image input, PDF input, Reasoning, Prompt caching, Computer use.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gmi/anthropic/claude-opus-4",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Claude Opus 4 cost?

Claude Opus 4 costs $15.00 per 1M input tokens and $75.00 per 1M output tokens from GMI Cloud, the lowest of 4 providers.

### What is the context window of Claude Opus 4?

Claude Opus 4 has a 409,600-token context window and returns up to 32,000 tokens per response.

### Which providers offer Claude Opus 4?

Claude Opus 4 is available from 4 providers through LiteLLM: GMI Cloud, Amazon Bedrock, Databricks and Vercel AI Gateway. The lowest price is on GMI Cloud.

### How do I call Claude Opus 4 with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gmi/anthropic/claude-opus-4", or add the model to the LiteLLM proxy's config.yaml and send requests to /v1/chat/completions from any OpenAI client. LiteLLM tracks the cost of every request at the prices on this page.

### What features does Claude Opus 4 support?

Claude Opus 4 supports function calling, structured output, image input, PDF input, reasoning, prompt caching and computer use.

### When did LiteLLM add Claude Opus 4?

Claude Opus 4 was added to LiteLLM's model price file in May 2025.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json