# GPT-Realtime-2.1

> GPT-Realtime-2.1 is a proprietary language model from OpenAI, released on 6 Jul 2026. It accepts text, audio and images and generates text and audio, with a 128K-token context window and up to 32K output tokens per response. As of 4 Oct 2026, the lowest listed API price is $4 per million input tokens and $24 per million output tokens (OpenAI API), across 2 providers we track.

Source page: https://www.aimodel.directory/models/gpt-realtime-2-1
Last verified: 4 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 6 Jul 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Context window:** 128K (128,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Max output:** 32K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Knowledge cutoff:** 30 Sept 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Input:** Text, audio and images (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Output:** Text and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Reasoning mode:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)
- **Structured output:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/openai/models/gpt-realtime-2.1.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| OpenAI API | $4 | $24 | $0.40 | 128K |
| Vercel AI Gateway | $4 | $24 | $0.40 | 128K |

## FAQ

### What is the context window of GPT-Realtime-2.1?

GPT-Realtime-2.1 has a context window of 128,000 tokens (128K) and can generate up to 32,000 tokens in a single response, according to models.dev.

### How much does the GPT-Realtime-2.1 API cost?

Through OpenAI API, GPT-Realtime-2.1 costs $4 per million input tokens and $24 per million output tokens. Prices last verified 4 Oct 2026.

### Is GPT-Realtime-2.1 open source?

No. GPT-Realtime-2.1 is a proprietary model; OpenAI has not released its weights. It is available through APIs including OpenAI API, Vercel AI Gateway.

### When was GPT-Realtime-2.1 released?

OpenAI released GPT-Realtime-2.1 on 6 Jul 2026, according to models.dev.

### Which providers offer GPT-Realtime-2.1?

We track GPT-Realtime-2.1 on 2 providers: OpenAI API, Vercel AI Gateway.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "GPT-Realtime-2.1", https://www.aimodel.directory/models/gpt-realtime-2-1