# gpt-realtime-2

`gpt-realtime-2` — **openai** · SPEECH

> gpt-realtime-2 (gpt-realtime-2) is a speech model from openai with a 32K-token context window; capabilities tools; input audio, image, text; output audio, text.

| Field | Value |
| --- | --- |
| Vendor | openai |
| Kind | SPEECH |
| Context window | 32,000 tokens |
| Max output tokens | 4,096 tokens |
| Indicative price (US list) | $4 in / $16 out per 1M tokens (indicative US list — verify with vendor) |
| Input modalities | audio, image, text |
| Output modalities | audio, text |
| Capabilities | tools |
| Sources | committed, litellm, openai-api |
| Last verified | 2026-07-24 |

*Part of the [Model Catalog](https://openviglet.github.io/model-catalog/) — [openai models](https://openviglet.github.io/model-catalog/models/openai/) · [Vendor JSON](https://openviglet.github.io/model-catalog/by-vendor/openai.json) · [HTML](https://openviglet.github.io/model-catalog/models/openai/gpt-realtime-2.html)*