# GPT-3.5 Turbo

> OpenAI's legacy GPT model for chat and non-chat text tasks, with low per-token prices.

## Key facts

- Model author: OpenAI
- Input: $0.50 per 1M tokens
- Output: $1.50 per 1M tokens
- Context window: 16,385 tokens
- Maximum output: 4,096 tokens
- Input modalities: text
- Output modalities: text
- Capabilities: fine_tuning
- Released: 2023-05-28
- Knowledge cutoff: Sep 01, 2021
- Model IDs: `openai/gpt-3.5-turbo`
- Model page: https://www.realrelay.ai/model/openai/gpt-3.5-turbo

## Overview

GPT-3.5 Turbo is a legacy GPT model from OpenAI that understands and generates natural language or code. It is optimized for chat through the Chat Completions interface and works for non-chat tasks as well. It handles text input and output, and OpenAI lists it as deprecated.

GPT-3.5 Turbo has a context window of 16,385 tokens and can generate up to 4,096 output tokens. It accepts text input and returns text output. Its knowledge cutoff is September 1, 2021, and it was released on May 28, 2023.

## Capabilities

GPT-3.5 Turbo reads text and returns text, covering multi-turn chat as well as non-chat natural language and code tasks.

OpenAI also offers it as dated snapshots, which lock in a specific version of the model so that behavior stays consistent.

## Pricing

GPT-3.5 Turbo is billed per token: $0.50 per 1M input tokens and $1.50 per 1M output tokens. GPT-3.5 Turbo is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-3.5 Turbo for text-only chat assistants and support-style conversations, where the prompt and the reply fit inside a context window of 16,385 tokens.

It also covers non-chat jobs such as rewriting text or drafting code snippets at a low per-token price, for workloads that already depend on this model. Up to 4,096 output tokens are available per reply.

## Call it

OpenAI-compatible chat completions:

```bash
curl https://www.realrelay.ai/v1/chat/completions \
  -H "Authorization: Bearer $REALRELAY_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "openai/gpt-3.5-turbo", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-3.5 Turbo?

GPT-3.5 Turbo is a legacy GPT model from OpenAI that understands and generates natural language or code. It is optimized for chat through the Chat Completions interface and works for non-chat tasks as well. It handles text input and output, and OpenAI lists it as deprecated.

### 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.

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

GPT-3.5 Turbo has a context window of 16,385 tokens and can generate up to 4,096 output tokens.

### What inputs and outputs does GPT-3.5 Turbo support?

GPT-3.5 Turbo accepts text input and returns text output.

### When was GPT-3.5 Turbo released?

GPT-3.5 Turbo was released on May 28, 2023. Its knowledge cutoff is September 1, 2021.

### How do I call GPT-3.5 Turbo through the API?

To call GPT-3.5 Turbo, send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-3.5-turbo.