Experiential
ModelsObservability
Star us on GitHubJoin the DiscordDocs
Sign in
Continue with GoogleContinue with GitHub
or
Models

GPT Realtime 2.1

gpt-realtime-2.1by GPTnot yet callable via API

Context

no data

Max output

no data

Price per million tokens

no datainno dataout

Released

-

This model produces audio output, which the API does not serve yet. It is not listed by GET /v1/models. Text, image, embedding, speech, transcription, and video models are callable today.
CapabilitiesAccepts text, audio

Sampling

Stop sequences

Tools & structure

Parallel tool calls

Streaming

Streaming

Limits

Max-tokens fieldmax_tokens

Sending an unsupported field? See error referenceAzure OpenAI docs

Providers serving this model2
Status
Azure Foundrygpt-realtime-2.1-2026-07-07deployed 2026-07-07no datano data99.9%-no datano data$0.61≈$2.94≈no data≈-no datadisabledestimated
Azure Foundrygpt-realtime-2.1no datano data99.9%-no datano datano datano datano data-no datadisabled-
Release notes