# GPT Realtime Mini (2025-12-15)

> A cost-efficient version of GPT Realtime - 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-mini-2025-12-15`
- Status: available; stops working on 2027-01-20, use openai/gpt-realtime-2.1-mini instead
- Released: 2025-12-15
- Context: 32K tokens
- Max output: 4K tokens
- Input: text, audio, image; output: text, audio

## Prices (USD)

| Item | Price | Unit |
| --- | --- | --- |
| Input | $0.66 | per 1M tokens |
| Output | $2.64 | per 1M tokens |
| Cache read | $0.066 | per 1M tokens |
| Audio input | $11.00 | per 1M tokens |
| Audio output | $22.00 | per 1M tokens |
| Image input | $0.88 | per 1M tokens |
| audio.input.cached | $0.33 |  |
| image.io.input.cached | $0.088 |  |

## 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 | $0.66 | $2.64 | no |

Web page: https://www.ohmygpt.com/models/openai/gpt-realtime-mini-2025-12-15