# GPT-4 API Pricing

As of October 10, 2026, GPT-4 costs $30.00 per 1M input tokens and $60.00 per 1M output tokens on OpenAI. It has an 8,192-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/gpt-4
- Lab: OpenAI
- LiteLLM model name: `gpt-4`
- Context window: 8,192 tokens
- Max output: 4,096 tokens
- Deprecation date: October 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 | `gpt-4` | $30.00 | $60.00 | – | – | – | 8K |
| OpenAI (snapshot 0613) | `gpt-4-0613` | $30.00 | $60.00 | – | – | – | 8K |
| OpenAI (fine-tuned, snapshot 0613) | `ft:gpt-4-0613` | $30.00 | $60.00 | – | – | – | 8K |
| Azure OpenAI | `azure/gpt-4` | $30.00 | $60.00 | – | – | – | 8K |
| Azure OpenAI (snapshot 0613) | `azure/gpt-4-0613` | $30.00 | $60.00 | – | – | – | 8K |
| GitHub Copilot | `github_copilot/gpt-4` | – | – | – | – | – | 32K |
| GitHub Copilot (snapshot 0613) | `github_copilot/gpt-4-0613` | – | – | – | – | – | 32K |

## Cost examples

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

- OpenAI: $90.00
- Azure OpenAI: $90.00

## Features

Supported: Function calling, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gpt-4",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-4 cost?

GPT-4 costs $30.00 per 1M input tokens and $60.00 per 1M output tokens on OpenAI.

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

GPT-4 has an 8,192-token context window and returns up to 4,096 tokens per response.

### Which providers offer GPT-4?

GPT-4 is available from 3 providers through LiteLLM: OpenAI, Azure OpenAI and GitHub Copilot.

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

Use the LiteLLM Python SDK with model="gpt-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 GPT-4 support?

GPT-4 supports function calling and prompt caching.

### Is GPT-4 being deprecated?

OpenAI lists a deprecation date of October 23, 2026 for gpt-4.

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