# GPT-4 Turbo (2024-04-09)

> OpenAI's high-intelligence GPT model that reads text and images, calls tools and returns text.

## 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-2024-04-09`
- Model page: https://www.realrelay.ai/model/openai/gpt-4-turbo-2024-04-09

## Overview

GPT-4 Turbo (2024-04-09) is a dated snapshot of OpenAI's GPT-4 Turbo, which OpenAI describes as an older high-intelligence GPT model. It accepts text and image input, supports tool calling and returns text, with a context window of 128,000 tokens. The snapshot keeps an integration on one fixed model version.

GPT-4 Turbo (2024-04-09) has a context window of 128,000 tokens and can generate up to 4,096 output tokens. It accepts text and image input and returns text output. Its knowledge cutoff is December 1, 2023, and it was released on April 9, 2024.

## Capabilities

GPT-4 Turbo (2024-04-09) supports tool calling and image input alongside text. It returns text output, with up to 4,096 tokens per request.

As a dated snapshot, it keeps one model version fixed. Its knowledge cutoff is December 1, 2023.

## Pricing

GPT-4 Turbo (2024-04-09) is billed per token: $10.00 per 1M input tokens and $30.00 per 1M output tokens. GPT-4 Turbo (2024-04-09) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-4 Turbo (2024-04-09) for assistants that read screenshots, charts or scanned pages together with a question and answer in text, using the 128,000-token window for longer inputs.

Its tool calling lets an application hand the model functions to call, which suits chat agents that look up data or trigger actions before they 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-4-turbo-2024-04-09", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-4 Turbo (2024-04-09)?

GPT-4 Turbo (2024-04-09) is a dated snapshot of OpenAI's GPT-4 Turbo, which OpenAI describes as an older high-intelligence GPT model. It accepts text and image input, supports tool calling and returns text, with a context window of 128,000 tokens. The snapshot keeps an integration on one fixed model version.

### How much does GPT-4 Turbo (2024-04-09) cost?

GPT-4 Turbo (2024-04-09) costs $10.00 per 1M input tokens and $30.00 per 1M output tokens.

### What is the context window of GPT-4 Turbo (2024-04-09)?

GPT-4 Turbo (2024-04-09) has a context window of 128,000 tokens and can generate up to 4,096 output tokens.

### What inputs and outputs does GPT-4 Turbo (2024-04-09) support?

GPT-4 Turbo (2024-04-09) accepts text and image input and returns text output.

### Which features does GPT-4 Turbo (2024-04-09) support?

GPT-4 Turbo (2024-04-09) supports tool calling and image input.

### When was GPT-4 Turbo (2024-04-09) released?

GPT-4 Turbo (2024-04-09) was released on April 9, 2024. Its knowledge cutoff is December 1, 2023.

### How do I call GPT-4 Turbo (2024-04-09) through the API?

To call GPT-4 Turbo (2024-04-09), send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-4-turbo-2024-04-09.