# Introducing gpt-realtime

*Source* · `src-openai-2025-gpt-realtime` · status: **n/a**

| field | value |
|---|---|
| kind | Technical report / blog |
| authors | OpenAI |
| venue | OpenAI blog |
| date | 2025-08-28 |
| url | https://openai.com/index/introducing-gpt-realtime/ |
| accessed | 2026-10-24 |

## Notes

gpt-realtime: Big Bench Audio 82.8% vs 65.6%, MultiChallenge 30.5% vs 20.6%, ComplexFuncBench 66.5% vs 49.7% versus the December 2024 model; audio $32 per 1M input ($0.40 cached) and $64 per 1M output, 20% below gpt-4o-realtime-preview.

## Backlinks (computed)

**cited by:** [Realtime speech-to-speech and expressive TTS for characters](../technique/realtime-voice-models.md)

## Citation

OpenAI (2025-08-28). *Introducing gpt-realtime*. OpenAI blog https://openai.com/index/introducing-gpt-realtime/

---
Provenance: created in run `2026-10-24-techniques-llm-agents`.
