# GPT Realtime

> This is our first general-availability realtime model, capable of responding to audio and text inputs in realtime over WebRTC, WebSocket, or SIP connections.

Agent resources: the index of everything machine-readable is https://www.ohmygpt.com/llms.txt; the integration skill (endpoints, auth, SDK and coding-tool setup) is https://www.ohmygpt.com/skill.md.

- Model ID: `openai/gpt-realtime`
- Status: stops working on 2027-01-20, use openai/gpt-realtime-2.1 instead
- Live status and providers as JSON, no key needed: https://api.ohmygpt.com/v1/models/openai/gpt-realtime
- Released: 2025-10-07
- Context: 32K tokens
- Max output: 4K tokens
- Input: text, audio, image; output: text, audio

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $4.40 | per 1M tokens |
| Output | $17.60 | per 1M tokens |
| Cache read | $0.44 | per 1M tokens |
| Audio input | $35.20 | per 1M tokens |
| Audio cache read | $0.44 | per 1M tokens |
| Audio output | $70.40 | per 1M tokens |
| Image input | $5.50 | per 1M tokens |
| Image cache read | $0.55 | per 1M tokens |

## Providers

This model chooses its provider itself; a provider prefix is not accepted.

| Provider | Pinned model ID | Location | Input | Output | Trains on your data |
| --- | --- | --- | --- | --- | --- |
| OpenAI | — | United States | $4.40 | $17.60 | no |

Web page: https://www.ohmygpt.com/models/openai/gpt-realtime