# GPT-3.5 Turbo API Pricing

As of October 10, 2026, GPT-3.5 Turbo costs $0.50 per 1M input tokens and $1.50 per 1M output tokens on OpenAI. Across 4 providers on LiteLLM, the input price ranges from $0.50 to $1.00. It has a 16,385-token context window and returns up to 4,096 tokens per response.

- Page: https://models.litellm.ai/models/gpt-3.5-turbo
- Lab: OpenAI
- LiteLLM model name: `gpt-3.5-turbo`
- Context window: 16,385 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-3.5-turbo` | $0.50 | $1.50 | – | – | – | 16K |
| OpenAI (snapshot 0125) | `gpt-3.5-turbo-0125` | $0.50 | $1.50 | – | – | – | 16K |
| OpenAI (snapshot 1106) | `gpt-3.5-turbo-1106` | $1.00 | $2.00 | – | – | – | 16K |
| OpenAI (fine-tuned) | `ft:gpt-3.5-turbo` | $3.00 | $6.00 | – | – | – | 16K |
| OpenAI (fine-tuned, snapshot 0125) | `ft:gpt-3.5-turbo-0125` | $3.00 | $6.00 | – | – | – | 16K |
| OpenAI (fine-tuned, snapshot 0613) | `ft:gpt-3.5-turbo-0613` | $3.00 | $6.00 | – | – | – | 4K |
| OpenAI (fine-tuned, snapshot 1106) | `ft:gpt-3.5-turbo-1106` | $3.00 | $6.00 | – | – | – | 16K |
| Azure OpenAI | `azure/gpt-3.5-turbo` | $0.50 | $1.50 | – | – | – | 4K |
| GitHub Copilot | `github_copilot/gpt-3.5-turbo` | – | – | – | – | – | 16K |
| GitHub Copilot (snapshot 0613) | `github_copilot/gpt-3.5-turbo-0613` | – | – | – | – | – | 16K |
| Vercel AI Gateway | `vercel_ai_gateway/openai/gpt-3.5-turbo` | $0.50 | $1.50 | – | – | – | 16K |

## Cost examples

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

- OpenAI: $1.75
- Azure OpenAI: $1.75
- Vercel AI Gateway: $1.75

## Features

Supported: Function calling, Parallel tool calls, Prompt caching.

## Use it with LiteLLM

```python
from litellm import completion

response = completion(
    model="gpt-3.5-turbo",
    messages=[{"role": "user", "content": "Hello!"}],
)
```

## FAQ

### How much does GPT-3.5 Turbo cost?

GPT-3.5 Turbo costs $0.50 per 1M input tokens and $1.50 per 1M output tokens on OpenAI. Across 4 providers on LiteLLM, the input price ranges from $0.50 to $1.00.

### What is the context window of GPT-3.5 Turbo?

GPT-3.5 Turbo has a 16,385-token context window and returns up to 4,096 tokens per response.

### Which providers offer GPT-3.5 Turbo?

GPT-3.5 Turbo is available from 4 providers through LiteLLM: OpenAI, Azure OpenAI, GitHub Copilot and Vercel AI Gateway. The lowest price is on OpenAI.

### How do I call GPT-3.5 Turbo with an OpenAI-compatible API?

Use the LiteLLM Python SDK with model="gpt-3.5-turbo", 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-3.5 Turbo support?

GPT-3.5 Turbo supports function calling, parallel tool calls and prompt caching.

### Is GPT-3.5 Turbo being deprecated?

OpenAI lists a deprecation date of October 23, 2026 for gpt-3.5-turbo.

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