# GPT-4 O Preview API Pricing

GPT-4 O Preview is available through LiteLLM. It has a 64,000-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/gpt-4-o-preview
- Lab: OpenAI
- Context window: 64,000 tokens
- Max output: 4,096 tokens
- Added to LiteLLM: December 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 |
|---|---|---|---|---|---|---|---|
| GitHub Copilot | `github_copilot/gpt-4-o-preview` | – | – | – | – | – | 64K |

## Features

Supported: Function calling, Parallel tool calls.

## FAQ

### What is the context window of GPT-4 O Preview?

GPT-4 O Preview has a 64,000-token context window and returns up to 4,096 tokens per response.

### What features does GPT-4 O Preview support?

GPT-4 O Preview supports function calling and parallel tool calls.

### When did LiteLLM add GPT-4 O Preview?

GPT-4 O Preview was added to LiteLLM's model price file in December 2025.

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