# Claude Opus 5.5 Fast API Pricing

As of October 21, 2026, Claude Opus 5.5 Fast costs $8.00 per 1M input tokens and $40.00 per 1M output tokens on Azure AI Foundry, with cache reads at $0.40 and cache writes at $10.00 per 1M tokens. It has a 1,000,000-token context window and returns up to 128,000 tokens per response.

- Page: https://models.litellm.ai/models/claude-opus-5-5-fast
- Lab: Anthropic
- LiteLLM model name: `azure_ai/claude-opus-5-5-fast`
- Context window: 1,000,000 tokens
- Max output: 128,000 tokens
- Added to LiteLLM: October 15, 2026
- Deprecation date: October 1, 2027
- Prices updated: October 15, 2026

## Pricing by provider

Token prices in USD per 1M tokens.

| Provider | Model name | Input | Output | Cache read | Per image | Per second | Context |
|---|---|---|---|---|---|---|---|
| Azure AI Foundry | `azure_ai/claude-opus-5-5-fast` | $8.00 | $40.00 | $0.40 | – | – | 1M |

## Cost examples

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

- Azure AI Foundry: $36.00

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

- Azure AI Foundry: $88.00

## 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="azure_ai/claude-opus-5-5-fast",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## Cost calculator

10,000 requests a day with 1,000 input and 500 output tokens each, at Azure AI Foundry's price: $0.028 per request, $280 per day, $8,400 per month (30 days). Try other numbers at https://models.litellm.ai/calculator?model=claude-opus-5-5-fast

## FAQ

### How much does Claude Opus 5.5 Fast cost?

Claude Opus 5.5 Fast costs $8.00 per 1M input tokens and $40.00 per 1M output tokens on Azure AI Foundry, with cache reads at $0.40 and cache writes at $10.00 per 1M tokens.

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

Claude Opus 5.5 Fast has a 1,000,000-token context window and returns up to 128,000 tokens per response.

### Which providers offer Claude Opus 5.5 Fast?

Claude Opus 5.5 Fast is available from Azure AI Foundry through LiteLLM, using the model name azure_ai/claude-opus-5-5-fast.

### How do I call Claude Opus 5.5 Fast with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure_ai/claude-opus-5-5-fast", 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 5.5 Fast support?

Claude Opus 5.5 Fast supports function calling, structured output, image input, PDF input, reasoning, prompt caching and computer use.

### When did LiteLLM add Claude Opus 5.5 Fast?

Claude Opus 5.5 Fast was added to LiteLLM's model price file on October 15, 2026.

### Is Claude Opus 5.5 Fast being deprecated?

Azure AI Foundry lists a deprecation date of October 1, 2027 for azure_ai/claude-opus-5-5-fast.

Source: LiteLLM model price file, https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json. Maintainers update it from each provider's published pricing, and this page is usually rebuilt within 20 minutes of every change.