Cody
en
ENESFRDEJAKOPT-BRPLAR
Agents
Cody Assist logoCody AssistKnowledge and supportCody Convert logoCody ConvertProactive website agentCody Clear logoCody ClearCompliance-gradeCody Live logoCody LiveAvatars and experiences
All agentsPricing
Resources
BlogUse casesPrompt librarySkill libraryModel library
Company
AboutContact
All models
Voice & realtimeLive
OpenAI

GPT-Realtime-2.1

OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context.

Open provider docsSee key facts

Plain-English overview

What GPT-Realtime-2.1 actually is

GPT-Realtime-2.1 is designed for live conversations where the model must listen, speak, follow instructions, and call tools in one realtime session. OpenAI highlights improved interruption, silence, noise, and alphanumeric handling over the prior version.

Audio, text, and image input are billed in different token classes. A realistic budget therefore needs captured usage from full conversations, not a simple conversion from audio minutes alone.

Good fit for

  • Tool-using customer or employee voice agents
  • Multimodal realtime assistants
  • OpenAI-native agent stacks

Category comparison

The facts that matter for voice models

These are provider-published specifications, not Cody benchmark scores. Follow the linked sources for current limits and endpoint-specific exceptions.

Price basis
Audio $32 in · $64 out / 1M tokensToken-, character-, or minute-based price for the listed access route.
Interaction mode
Speech-to-speech with text/image contextSpeech-to-speech, audio-to-audio, or streamed text-to-speech behavior.
Published latency
Not publishedProvider-published measurement with its stated exclusions; not a Cody test.
Languages
Multilingual; exact list not published hereProvider-documented language coverage or a clear unpublished marker.
Tools & control
Function calling and configurable reasoningNative function calling, reasoning, or speech-control features.
Context or input limit
128K input · 32K max outputDocumented token or character limit where it is meaningful.

API and provider access

Where to get GPT-Realtime-2.1

OpenAIGPT-Realtime-2.1 model docsDirect realtime speech-to-speech access.

Availability

Regions and access stage

Available through OpenAI's Realtime API in supported countries and territories.

Direct access follows OpenAI's live supported-country list.

Check live availability

Data and training

The route matters.

OpenAI says API content is not used for training by default. Default abuse-monitoring logs may be retained up to 30 days, with additional controls available to qualifying organizations.

This is a concise reading of the cited provider material, not legal advice. A third-party gateway can have different storage, routing, training, and residency terms from the model maker's direct API.

Read the provider policy

Frequently asked questions

GPT-Realtime-2.1 FAQ

What is GPT-Realtime-2.1?

OpenAI's realtime speech-to-speech reasoning model for tool-using voice agents that also need text and image context. GPT-Realtime-2.1 is designed for live conversations where the model must listen, speak, follow instructions, and call tools in one realtime session. OpenAI highlights improved interruption, silence, noise, and alphanumeric handling over the prior version.

When was GPT-Realtime-2.1 released?

The provider does not publish a clear release date for GPT-Realtime-2.1 in the source material reviewed by Cody.

Where can I access GPT-Realtime-2.1?

Available through OpenAI's Realtime API in supported countries and territories. The access routes listed in this guide are OpenAI.

How much does GPT-Realtime-2.1 cost?

$32 audio input · $64 audio output / 1M tokens. Text is $4 input and $24 output per million tokens; image input is $5 per million tokens. Cached-input rates differ.

Where is GPT-Realtime-2.1 available?

Available through OpenAI's Realtime API in supported countries and territories. Direct access follows OpenAI's live supported-country list.

Is my GPT-Realtime-2.1 API data used for training?

OpenAI says API content is not used for training by default. Default abuse-monitoring logs may be retained up to 30 days, with additional controls available to qualifying organizations. The policy belongs to the provider route and account terms, so verify it again before production use.

Related comparisons

Head-to-head comparisons

View category →

  1. GPT-Realtime-2.1 vs GPT-Live 1

    OpenAI's full-duplex voice frontend for natural conversation that delegates deeper reasoning and actions to a separate backend agent.

    Open full comparison

  2. GPT-Realtime-2.1 vs Gemini 3.8 Live

    Google's real-time voice model for responsive conversations with audio, text and visual context.

    Open full comparison

  3. GPT-Realtime-2.1 vs Gemini 3.8 Live Extended Thinking

    A separate Gemini voice model that works through complex requests in the background while keeping the conversation going.

    Open full comparison

  4. GPT-Realtime-2.1 vs Gemini 3.1 Flash Live Preview

    Google's preview audio-to-audio model for low-latency dialogue with multimodal awareness, thinking, search grounding, and function calling.

    Open full comparison

  5. GPT-Realtime-2.1 vs Eleven v3 Conversational

    ElevenLabs' expressive realtime text-to-speech model for natural dialogue, emotional delivery, audio tags, and more than 70 languages.

    Open full comparison

  6. GPT-Realtime-2.1 vs Inworld Realtime TTS-2

    Inworld's newest expressive realtime text-to-speech model, designed to remember conversational delivery and speak in more than 100 languages.

    Open full comparison

  7. GPT-Realtime-2.1 vs Grok Voice Think Fast 2.0

    SpaceXAI's current realtime speech-to-speech model for sub-second conversational agents with tool access.

    Open full comparison