AI Model Radar
中文 EN

GPT-Realtime-2.1

OpenAI
Model overview

gpt-realtime-2.1

Realtime reasoning voice model with tool use and improved alphanumeric, noise, and interruption handling.

general LLMreasoningmultimodalaudiospeechrealtimeagentchatvoice assistantrealtime voiceenterprise access
CompareCompanyRankingsPublic signals
Representative version

gpt-realtime-2.1

CompanyOpenAI
Release2026-07-06
Release typeModel release
ParametersNot disclosed
ArchitectureNot disclosed
Context128,000
Input modalitiestext / image / audio
Output modalitiestext / audio
Tool use / function callingConfirmed: Tool use, Function calling
Structured output / reasoningConfirmed: Reasoning; Not shown: Structured output
Vision / audio / videoConfirmed: Vision, Audio; Not shown: Video
Open weights / LicenseNo open weights / license not applicable
openai-gpt-realtime-2-1-current · License not applicable
Vendor APIAvailable
GPT-Realtime-2.1 Model | OpenAI APIopenai-gpt-realtime-2-1-current · 2026-07-06
OpenRouterNot separately listed on OpenRouter
PricingOfficial · 2026-07-08: $4 / $24
input / output, per 1M tokens
BenchmarkNo reliable public source
Public signalsNo reliable public source
Use casesRealtime voice agents / Tool-using voice workflows / Low-latency spoken interaction / assistant chat
Claim evidenceRelease / model specs / weightsGPT-Realtime-2.1 Model | OpenAI APIgpt-realtime-2.1 · 2026-07-06
OpenRouter

Pricing / context / availability

OpenRouterNot separately listed on OpenRouter
OpenRouter listingNot separately listed in the current OpenRouter public list
Mapped versiongpt-realtime-2.1
openai-gpt-realtime-2-1-current
PricingOfficial · 2026-07-08: $4 / $24
input / output, per 1M tokens
Context128000
Speed/LatencyNo reliable public source
Snapshot time2026-07-15T20:11:41.551Z
SourceView source
Evidence gaps

Public display boundary

Parameter scale not disclosedOpenRouter not separately verifiedNo reliable benchmark sourceNo public model-card activity countersNo linkable real reviewSpeed/latency not disclosed