# GPT-4

> GPT-4 is a proprietary language model from OpenAI, released on 6 Nov 2023. It accepts text and generates text, with a 8K-token context window and up to 8K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $30 per million input tokens and $60 per million output tokens (OpenRouter), across 1 provider we track. OpenAI has deprecated this model.

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

## Specifications

- **Developer:** OpenAI
- **Release date:** 6 Nov 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Status:** Deprecated (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Context window:** 8K (8,192 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Max output:** 8K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Knowledge cutoff:** Nov 2023 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Input:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Output:** Text (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-4.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenRouter | $30 | $60 | – | 8K |

## FAQ

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

GPT-4 has a context window of 8,192 tokens (8K) and can generate up to 8,192 tokens in a single response, according to models.dev.

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

GPT-4 is listed from $30 per million input tokens and $60 per million output tokens (OpenRouter). Prices last verified 4 Oct 2026.

### Is GPT-4 open source?

No. GPT-4 is a proprietary model; OpenAI has not released its weights. It is available through APIs including OpenRouter.

### When was GPT-4 released?

OpenAI released GPT-4 on 6 Nov 2023, according to models.dev.

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