# GPT-4 Turbo

> An OpenAI model that accepts text and image input and returns text, reached through RealRelay's OpenAI-compatible endpoint.

## Key facts

- Model author: OpenAI
- Input: $10.00 per 1M tokens
- Output: $30.00 per 1M tokens
- Context window: 128,000 tokens
- Maximum output: 4,096 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: tools, vision
- Released: 2024-04-09
- Knowledge cutoff: Dec 01, 2023
- Model IDs: `openai/gpt-4-turbo`
- Model page: https://www.realrelay.ai/model/openai/gpt-4-turbo

## Overview

GPT-4 Turbo is an OpenAI model offered on RealRelay under the model ID openai/gpt-4-turbo. It accepts text and image input and returns text output, and calls use RealRelay's OpenAI-compatible endpoint.

The context window is 128,000 tokens and the maximum output is 4,096 tokens. The model was released on April 9, 2024, and its knowledge cutoff is December 1, 2023.

## Capabilities

Tool calling and vision are listed as supported capabilities. Text and image are the input modalities, and the output modality is text.

Within one request the context window is 128,000 tokens and the maximum output length is 4,096 tokens.

## Pricing

Pricing is metered by token. Input is $10.00 per 1M tokens and output is $30.00 per 1M tokens.

Each call made through RealRelay's OpenAI-compatible endpoint with the model ID openai/gpt-4-turbo is billed at those token rates.

## Use Cases

Because images are among the input modalities, a request can pair a picture with text instructions and receive text back, and tool calling is available when a request needs the model to return tool calls.

The 128,000-token context window and the 4,096-token maximum output set the length limit for each request.

To call it, set the model to openai/gpt-4-turbo in an OpenAI client and point the client at RealRelay.

## 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-4-turbo", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-4 Turbo?

GPT-4 Turbo is an OpenAI model that accepts text and image input and returns text output. On RealRelay it is called with the model ID openai/gpt-4-turbo.

### How is GPT-4 Turbo priced?

Input is $10.00 per 1M tokens and output is $30.00 per 1M tokens.

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

The context window is 128,000 tokens, and the maximum output is 4,096 tokens.

### Which input and output types does GPT-4 Turbo support?

GPT-4 Turbo accepts text and image input and returns text output.

### Does GPT-4 Turbo support tool calling?

Tool calling and vision are both listed as supported capabilities of the model.

### When was GPT-4 Turbo released?

GPT-4 Turbo was released on April 9, 2024, with a knowledge cutoff of December 1, 2023.

### How do I call GPT-4 Turbo through the OpenAI-compatible API?

Send a request to RealRelay's OpenAI-compatible endpoint with the model set to openai/gpt-4-turbo, including text, images, or both in the message content.