# GPT-4 32K API Pricing

As of October 10, 2026, GPT-4 32K costs $60.00 per 1M input tokens and $120.00 per 1M output tokens on Azure OpenAI. It has a 32,768-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/gpt-4-32k
- Lab: OpenAI
- LiteLLM model name: `azure/gpt-4-32k`
- Context window: 32,768 tokens
- Max output: 4,096 tokens
- Deprecation date: June 6, 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 |
|---|---|---|---|---|---|---|---|
| Azure OpenAI | `azure/gpt-4-32k` | $60.00 | $120.00 | – | – | – | 32K |
| Azure OpenAI (snapshot 0613) | `azure/gpt-4-32k-0613` | $60.00 | $120.00 | – | – | – | 32K |

## Cost examples

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

- Azure OpenAI: $180.00

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="azure/gpt-4-32k",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-4 32K cost?

GPT-4 32K costs $60.00 per 1M input tokens and $120.00 per 1M output tokens on Azure OpenAI.

### What is the context window of GPT-4 32K?

GPT-4 32K has a 32,768-token context window and returns up to 4,096 tokens per response.

### Which providers offer GPT-4 32K?

GPT-4 32K is available from Azure OpenAI through LiteLLM, using the model name azure/gpt-4-32k.

### How do I call GPT-4 32K with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="azure/gpt-4-32k", 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.

### Is GPT-4 32K being deprecated?

Azure OpenAI deprecated azure/gpt-4-32k on June 6, 2025.

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