LLM Reference

GPT Realtime Models by OpenAI

OpenAIProprietary
3 models2025Up to 32k ctxFrom $0.6/1M input

Last refreshed 2026-05-19. Next refresh: weekly.

Details

ResearcherOpenAI
LicenseProprietary
Commercial useCommercial use: conditional
Models3
Released2025
Max context32k

Capabilities

Vision1 of 3 models
MultimodalAll models
JSON / Tool use1 of 3 models

Links

Website

About

OpenAI realtime voice models for text, audio, and image inputs with text and audio outputs over the Realtime API.

Decision facts

Best fit
realtime voicevision and multimodal workJSON / Tool use
Capability starting point
gpt-realtime with 32k context and multimodal inputs
Lowest tracked input
gpt-realtime-mini · $0.6/1M · OpenAI API
Closest related family
GPT-5

Current Variants

Use-when guidance is based on each model's tracked capabilities, context window, release date, and replacement status.

2 in view1 retired

Use when the workload needs realtime voice, 32k context, and multimodal inputs.

2025-10realtime voice32k contextmultimodal inputs

Use when the workload needs realtime voice, 32k context, and multimodal inputs.

2025-10realtime voice32k contextmultimodal inputs

Release Timeline

2 release groups
2025-12
1 retired
gpt-realtime-1.5
realtime voice32k contextJSON / Tool use
Replaced
2025-10
2 current
gpt-realtime
realtime voice32k contextmultimodal inputs
Current
gpt-realtime-mini
realtime voice32k contextmultimodal inputs
Current

Replaced By

Keep for legacy integrations; evaluate GPT Realtime 2 before new work.

Specifications(3 models)

GPT Realtime model specifications comparison
ModelReleasedContextVisionMultimodalJSON / Tool use
gpt-realtime2025-1032kNoYesNo
gpt-realtime-mini2025-1032kNoYesNo

Available From(1 provider)

Pricing

GPT Realtime model pricing by provider
ModelProviderInput / 1MOutput / 1MType
gpt-realtime-miniOpenAI API$0.6$2.4Serverless
gpt-realtimeOpenAI API$4$16Serverless

Popular comparisons in this family