# GPT-5.3 Chat API Pricing

As of October 10, 2026, GPT-5.3 Chat costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens. It has a 128,000-token context window and returns up to 16,384 tokens per response.

- Page: https://models.litellm.ai/models/gpt-5.3-chat
- Lab: OpenAI
- LiteLLM model name: `gpt-5.3-chat-latest`
- Context window: 128,000 tokens
- Max output: 16,384 tokens
- Added to LiteLLM: March 2026
- Deprecation date: August 10, 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 (latest alias) | `gpt-5.3-chat-latest` | $1.75 | $14.00 | $0.175 | – | – | 128K |
| Azure OpenAI | `azure/gpt-5.3-chat` | $1.75 | $14.00 | $0.175 | – | – | 109K |
| ChatGPT Subscription (latest alias) | `chatgpt/gpt-5.3-chat-latest` | – | – | – | – | – | 128K |
| Azure OpenAI (eu) | `azure/eu/gpt-5.3-chat` | $1.925 | $15.40 | $0.1925 | – | – | 109K |
| Azure OpenAI (us) | `azure/us/gpt-5.3-chat` | $1.925 | $15.40 | $0.1925 | – | – | 109K |

## Cost examples

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

- OpenAI: $10.50
- Azure OpenAI: $10.50

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

- OpenAI: $20.30
- Azure OpenAI: $20.30

## Features

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

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gpt-5.3-chat-latest",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-5.3 Chat cost?

GPT-5.3 Chat costs $1.75 per 1M input tokens and $14.00 per 1M output tokens on OpenAI, with cache reads at $0.175 per 1M tokens.

### What is the context window of GPT-5.3 Chat?

GPT-5.3 Chat has a 128,000-token context window and returns up to 16,384 tokens per response.

### Which providers offer GPT-5.3 Chat?

GPT-5.3 Chat is available from 3 providers through LiteLLM: OpenAI, Azure OpenAI and ChatGPT Subscription.

### How do I call GPT-5.3 Chat with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-5.3-chat-latest", 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-5.3 Chat support?

GPT-5.3 Chat supports function calling, parallel tool calls, structured output, image input, PDF input and reasoning. It does not support prompt caching.

### When did LiteLLM add GPT-5.3 Chat?

GPT-5.3 Chat was added to LiteLLM's model price file in March 2026.

### Is GPT-5.3 Chat being deprecated?

OpenAI deprecated gpt-5.3-chat-latest on August 10, 2026.

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