# GPT-4o

> GPT-4o is a proprietary language model from OpenAI, released on 13 May 2024. It accepts text, images and PDFs and generates text, with a 128K-token context window and up to 16K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $2.50 per million input tokens and $10 per million output tokens (OpenAI API), across 3 providers we track.

Source page: https://www.aimodel.directory/models/gpt-4o
Last verified: 4 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 13 May 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Max output:** 16K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Knowledge cutoff:** Sept 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Input:** Text, images and PDFs (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)
- **Structured output:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4o.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenAI API | $2.50 | $10 | $1.25 | 128K |
| OpenAI API | $2.50 | $10 | $1.25 | 128K |
| OpenAI API | $2.50 | $10 | $1.25 | 128K |
| OpenRouter | $2.50 | $10 | $1.25 | 128K |
| OpenRouter | $2.50 | $10 | $1.25 | 128K |
| Vercel AI Gateway | $2.50 | $10 | $1.25 | 128K |
| OpenRouter | $2.50 | $10 | $1.25 | 128K |
| Vercel AI Gateway | $4.25 | $17 | $2.13 | 128K |
| OpenRouter | $5 | $15 | – | 128K |

## FAQ

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

GPT-4o has a context window of 128,000 tokens (128K) and can generate up to 16,384 tokens in a single response, according to models.dev.

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

Through OpenAI API, GPT-4o costs $2.50 per million input tokens and $10 per million output tokens. Prices last verified 4 Oct 2026.

### Is GPT-4o open source?

No. GPT-4o is a proprietary model; OpenAI has not released its weights. It is available through APIs including OpenAI API, OpenRouter, Vercel AI Gateway.

### When was GPT-4o released?

OpenAI released GPT-4o on 13 May 2024, according to models.dev.

### Which providers offer GPT-4o?

We track GPT-4o on 3 providers: OpenAI API, OpenRouter, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "GPT-4o", https://www.aimodel.directory/models/gpt-4o