Meet the team that turns your ideas into work.

Discover EightBots
EIGHTBOTS
Contact salesSign up
OpenAIGPT Realtime

GPT-Realtime

GPT-Realtime was OpenAI's first generally available Realtime model. It is now deprecated and remains relevant to applications built around its 2025 release.

Deprecated API; check access details

The original general-availability voice contract

Its documented connections include WebRTC, WebSocket and SIP. Text, audio and images can enter the session, with text or audio output. The model has a 32,000-token window and a 4,096-token output limit.GPT-Realtime official model documentation

Review an existing integration

Practical guidance. Review the audio connection and event handling when moving to a newer voice model. Include interrupted speech, silence and tools in a complete call. Changing the model ID alone does not verify that the conversation state remains correct.

Specifications & access

GPT-Realtime specifications
DetailValue and conditions
StatusDeprecated API; check access details
AccessAPI
Model identifiersgpt-realtimegpt-realtime-2025-08-28
Context window32,000 tokens

Published context for this deprecated release

GPT-Realtime official model documentation
Maximum output4,096 tokens

Published maximum output, bounded by the remaining context

GPT-Realtime official model documentation
Provider statusDeprecated in the current OpenAI model catalog; confirm remaining account access.GPT-Realtime official model documentation

Related models

  • GPT-Realtime-2.1

    OpenAI · GPT Realtime

    GPT-Realtime-2.1 combines conversational audio with reasoning and tool use.

    Launch date not confirmedAPI
  • GPT-Realtime-2

    OpenAI · GPT Realtime

    GPT-Realtime-2 is a speech-to-speech model with configurable reasoning and tools.

    Launch date not confirmedAPI

  • GPT-Realtime-2.1 Mini is a distilled voice-reasoning model for lower-cost interactive audio.

    Launch date not confirmedAPI

  • GPT-Realtime-Translate converts incoming speech into translated speech and text while the source audio is still arriving.

    Launch date not confirmedAPI