# GPT-Realtime-1.5

> GPT-Realtime-1.5 is a proprietary language model from OpenAI, released on 23 Feb 2026. It accepts text and audio and generates text and audio, with a 32K-token context window and up to 4K output tokens per response. As of 21 Oct 2026, the lowest listed API price is $4 per million input tokens and $16 per million output tokens (Vercel AI Gateway), across 1 provider we track.

Source page: https://www.aimodel.directory/models/gpt-realtime-1-5
Last verified: 21 Oct 2026

## Specifications

- **Developer:** OpenAI
- **Release date:** 23 Feb 2026 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Status:** Generally available (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Weights:** Proprietary (API only) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Context window:** 32K (32,000 tokens) (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Max output:** 4K tokens (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Knowledge cutoff:** 30 Sept 2024 (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Input:** Text and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Output:** Text and audio (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Reasoning mode:** No (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)
- **Tool calling:** Yes (source: models.dev, https://github.com/sst/models.dev/blob/dev/providers/vercel/models/openai/gpt-realtime-1.5.toml)

## API pricing (USD per 1M tokens)

| Provider | Input | Output | Cached input | Context |
|---|---|---|---|---|
| Vercel AI Gateway | $4 | $16 | $0.40 | 32K |

## FAQ

### What is the context window of GPT-Realtime-1.5?

GPT-Realtime-1.5 has a context window of 32,000 tokens (32K) and can generate up to 4,096 tokens in a single response, according to models.dev.

### How much does the GPT-Realtime-1.5 API cost?

GPT-Realtime-1.5 is listed from $4 per million input tokens and $16 per million output tokens (Vercel AI Gateway). Prices last verified 21 Oct 2026.

### Is GPT-Realtime-1.5 open source?

No. GPT-Realtime-1.5 is a proprietary model; OpenAI has not released its weights. It is available through APIs including Vercel AI Gateway.

### When was GPT-Realtime-1.5 released?

OpenAI released GPT-Realtime-1.5 on 23 Feb 2026, according to models.dev.

---
Data licensed CC BY 4.0. Cite as: AI Model Directory, "GPT-Realtime-1.5", https://www.aimodel.directory/models/gpt-realtime-1-5