# GPT-4o

> OpenAI's omni GPT model for text and image input, with tool calling and structured text output.

## Key facts

- Model author: OpenAI
- Input: $2.50 per 1M tokens
- Output: $10.00 per 1M tokens
- Cached input: $1.25 per 1M tokens
- Context window: 128,000 tokens
- Maximum output: 16,384 tokens
- Input modalities: image, text
- Output modalities: text
- Capabilities: structured_output, tools, vision
- Released: 2024-05-13
- Knowledge cutoff: Oct 01, 2023
- Model IDs: `openai/gpt-4o`
- Model page: https://www.realrelay.ai/model/openai/gpt-4o

## Overview

GPT-4o is OpenAI's omni model, a fast, intelligent and flexible GPT model for general work. It accepts text and image inputs and produces text outputs, including structured output. It supports tool calling and has a context window of 128,000 tokens.

GPT-4o has a context window of 128,000 tokens and can generate up to 16,384 output tokens. It accepts text and image input and returns text output. Its knowledge cutoff is October 1, 2023, and it was released on May 13, 2024.

## Capabilities

GPT-4o supports tool calling, structured output and image input, and it returns text. It can generate up to 16,384 output tokens per request.

Cached input reads are priced separately, which lowers the cost of prompts that repeat a long shared prefix.

## Pricing

GPT-4o is billed per token: $2.50 per 1M input tokens and $10.00 per 1M output tokens. Cached input reads cost $1.25 per 1M tokens. GPT-4o is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-4o for assistants that combine pictures and text, such as reading a screenshot, a receipt or a chart and answering questions about it in plain text.

Its structured output and tool calling make it a fit for applications that extract fields into a fixed format or call functions during a conversation.

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

## FAQ

### What is GPT-4o?

GPT-4o is OpenAI's omni model, a fast, intelligent and flexible GPT model for general work. It accepts text and image inputs and produces text outputs, including structured output. It supports tool calling and has a context window of 128,000 tokens.

### How much does GPT-4o cost?

GPT-4o costs $2.50 per 1M input tokens and $10.00 per 1M output tokens, with cached input reads at $1.25 per 1M tokens.

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

GPT-4o has a context window of 128,000 tokens and can generate up to 16,384 output tokens.

### What inputs and outputs does GPT-4o support?

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

### Which features does GPT-4o support?

GPT-4o supports tool calling, structured output and image input.

### When was GPT-4o released?

GPT-4o was released on May 13, 2024. Its knowledge cutoff is October 1, 2023.

### How do I call GPT-4o through the API?

To call GPT-4o, send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-4o.