Using GPT Realtime 2.1 on Microsoft Foundry

Implementation guide · GPT Realtime 2 · OpenAI

Serverless

Microsoft Foundry exposes GPT Realtime 2.1 through model ID gpt-realtime-2.1. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-10-19. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at Microsoft Foundry and generate an API key.
  2. 2
    Use the Microsoft Foundry SDK or REST API to call gpt-realtime-2.1 — see the documentation for request format.
  3. 3
    You'll be billed $4.00/1M input, $24.00/1M output tokens. See full pricing.
API PortalDocumentationPricingModel Card

Code Examples

See Microsoft Foundry documentation for integration details.

Pricing on Microsoft Foundry

TypePrice (per 1M)
Input tokens$4.00
Output tokens$24.00

Capabilities

VisionMultimodalReasoningAudio

About GPT Realtime 2.1

OpenAI Realtime API flagship speech-to-speech model (gpt-realtime-2.1) with text/audio/image input, text/audio output, 128K context, reasoning token support.

Full model details →

Model Specs

Released2026-07-06
Context128K
Knowledge cutoff2024-09

More Models on Microsoft Foundry

GPT Realtime 2.1 Mini
All models on Microsoft Foundry →

Also available on(2)

OpenAI API$4.00/1MVercel AI Gateway$4.00/1M
Compare all providers →

Provider

Microsoft Foundry

Microsoft

Redmond, Washington, United States