# GPT-4o (2024-05-13)

> The May 13, 2024 snapshot of OpenAI's GPT-4o, which reads text and images and returns text.

## Key facts

- Model author: OpenAI
- Input: $5.00 per 1M tokens
- Output: $15.00 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-2024-05-13`
- Model page: https://www.realrelay.ai/model/openai/gpt-4o-2024-05-13

## Overview

GPT-4o (2024-05-13) is the dated snapshot of OpenAI's GPT-4o, where the o stands for omni. It accepts text and image inputs and produces text outputs, including structured output, with tool calling support. Pinning this snapshot keeps an integration on the version released on May 13, 2024.

GPT-4o (2024-05-13) 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 (2024-05-13) supports tool calling, structured output and image input, and it returns text. It has a context window of 128,000 tokens and can generate up to 16,384 output tokens.

Its knowledge cutoff is October 1, 2023. The dated name makes sure requests keep using this release instead of a model that changes over time.

## Pricing

GPT-4o (2024-05-13) is billed per token: $5.00 per 1M input tokens and $15.00 per 1M output tokens. GPT-4o (2024-05-13) is available through RealRelay's OpenAI-compatible API.

## Use cases

Use GPT-4o (2024-05-13) for multimodal assistants that read a photo, screenshot or chart together with a question and answer in text, or that return structured output for downstream code.

It also suits agent workflows where the model calls functions, so teams that validated this release can keep its behavior unchanged. Pinning the dated name avoids behavior changes between releases.

## 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-2024-05-13", "messages": [{"role": "user", "content": "Hello"}]}'
```

## FAQ

### What is GPT-4o (2024-05-13)?

GPT-4o (2024-05-13) is the dated snapshot of OpenAI's GPT-4o, where the o stands for omni. It accepts text and image inputs and produces text outputs, including structured output, with tool calling support. Pinning this snapshot keeps an integration on the version released on May 13, 2024.

### How much does GPT-4o (2024-05-13) cost?

GPT-4o (2024-05-13) costs $5.00 per 1M input tokens and $15.00 per 1M output tokens.

### What is the context window of GPT-4o (2024-05-13)?

GPT-4o (2024-05-13) has a context window of 128,000 tokens and can generate up to 16,384 output tokens.

### What inputs and outputs does GPT-4o (2024-05-13) support?

GPT-4o (2024-05-13) accepts text and image input and returns text output.

### Which features does GPT-4o (2024-05-13) support?

GPT-4o (2024-05-13) supports tool calling, structured output and image input.

### When was GPT-4o (2024-05-13) released?

GPT-4o (2024-05-13) was released on May 13, 2024. Its knowledge cutoff is October 1, 2023.

### How do I call GPT-4o (2024-05-13) through the API?

To call GPT-4o (2024-05-13), send a request to RealRelay's OpenAI-compatible API with the model ID openai/gpt-4o-2024-05-13.