Realtime voice - verified
Realtime voice API pricing by provider
5 realtime voice models from OpenAI, Gemini API and AssemblyAI, read on October 18, 2026. Some bill per audio token and some per minute; each price is shown exactly as the provider states it.
Every realtime voice model
Prices stay in the provider's own unit: per 1M audio tokens, per minute or per hour. A per-token price is not converted to minutes, because the audio a token buys differs by model. Open a model for its quotes and sources.
| Model | Priceprovider's own unit | Streaming | Languages | Limits | Features | Status |
|---|---|---|---|---|---|---|
| No models match these filters. | ||||||
GPT-Realtime-2.1OpenAI - gpt-realtime-2.1 | $32.00 per 1M audio input tokens; $0.40 cached; $64.00 per 1M audio output tokensdevelopers.openai.com | Not stated | Not stated | Not stated |
| current (no preview label) |
GPT-Realtime-2.1 MiniOpenAI - gpt-realtime-2.1-mini | $10.00 per 1M audio input tokens; $0.30 cached; $20.00 per 1M audio output tokensdevelopers.openai.com | Yes | Not stated | Not stated | None recorded | current (no preview label) |
GPT-Live 1OpenAI - gpt-live-1 | $0.05 per minutedevelopers.openai.com | Yes | Not stated | Not stated |
| current (no preview label) |
Gemini 3.8 LiveGemini API - gemini-3.8-live | $3.00 per 1M audio input tokens ($0.005/min); $12.00 per 1M audio output tokens ($0.018/min)ai.google.dev | Yes | Not stated | 131,072 input tokens / 65,536 output tokens |
| stable |
Voice Agent APIAssemblyAI - Voice Agent API | $4.50/hr ($0.075/min)assemblyai.com | Yes | 32 languages (STT layer) | Not stated |
| Not stated |
FAQ
How are realtime voice APIs priced?
Per audio token: OpenAI GPT-Realtime-2.1, OpenAI GPT-Realtime-2.1 Mini and Gemini 3.8 Live. Per minute or hour: OpenAI GPT-Live 1 at $0.05 per minute; AssemblyAI Voice Agent API at $4.50/hr ($0.075/min). Each price is copied as the provider states it.
Verified from each provider's own pricing pages and model docs; every quote was string-matched against the page that day. Prices are shown in the provider's own unit. Values marked derived were counted by us or taken from Azure's Retail Prices API, not from a pricing page. Prices change without notice; check the linked source before you commit a budget to one.
Newsletter
Know when a speech API changes its prices
One email per week. New model releases, pricing changes and what they mean for what you build.
Keep exploring
Speech-to-text API pricing
Every transcription price, plus a labelled $/hour conversion.
Text-to-speech API pricing
Per character, per token and credit prices, grouped by unit.
GPT-Live voice architecture
How OpenAI's live voice model fits a voice agent.
OpenAI Realtime API guide
Getting started with realtime voice sessions.