# Computer Use Preview API Pricing

As of October 10, 2026, Computer Use Preview costs $3.00 per 1M input tokens and $12.00 per 1M output tokens on OpenAI. It has an 8,192-token context window and returns up to 1,024 tokens per response.

- Page: https://models.litellm.ai/models/computer-use-preview
- Lab: OpenAI
- LiteLLM model name: `computer-use-preview`
- Context window: 8,192 tokens
- Max output: 1,024 tokens
- Added to LiteLLM: April 2025
- Deprecation date: July 23, 2026
- 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 |
|---|---|---|---|---|---|---|---|
| OpenAI | `computer-use-preview` | $3.00 | $12.00 | – | – | – | 8K |
| Azure OpenAI | `azure/computer-use-preview` | $3.00 | $12.00 | – | – | – | 8K |
| Azure OpenAI (eu) | `azure/eu/computer-use-preview` | $3.30 | $13.20 | – | – | – | – |
| Azure OpenAI (us) | `azure/us/computer-use-preview` | $3.30 | $13.20 | – | – | – | – |

## Cost examples

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

- OpenAI: $12.00
- Azure OpenAI: $12.00

## Features

Supported: Function calling, Parallel tool calls, Image input, PDF input, Reasoning.
Not supported: Structured output, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="computer-use-preview",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does Computer Use Preview cost?

Computer Use Preview costs $3.00 per 1M input tokens and $12.00 per 1M output tokens on OpenAI.

### What is the context window of Computer Use Preview?

Computer Use Preview has an 8,192-token context window and returns up to 1,024 tokens per response.

### Which providers offer Computer Use Preview?

Computer Use Preview is available from 2 providers through LiteLLM: OpenAI and Azure OpenAI.

### How do I call Computer Use Preview with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="computer-use-preview", 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 Computer Use Preview support?

Computer Use Preview supports function calling, parallel tool calls, image input, PDF input and reasoning. It does not support structured output and prompt caching.

### When did LiteLLM add Computer Use Preview?

Computer Use Preview was added to LiteLLM's model price file in April 2025.

### Is Computer Use Preview being deprecated?

OpenAI deprecated computer-use-preview on July 23, 2026.

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