GPT-Realtime-2.1 API Pricing

OpenAI · other available · Rates verified .

Verification unresolved or overdue: these are the last recorded rates. Confirm the current official rate before budgeting.

Published rates and billing units

Billing dimensionUSD list price
Text input / 1M tokens$4.00
Cached text input / 1M tokens$0.40
Text output / 1M tokens$24.00
Audio input / 1M tokens$32.00
Cached audio input / 1M tokens$0.40
Audio output / 1M tokens$64.00
Image input / 1M tokens$5.00
Cached image input / 1M tokens$0.50

Verified 2026-10-20 · Official source · Pricing methodology. Taxes, optional services and account-specific discounts are not included.

OpenAI realtime pricing history

USD · units shown per rate
● Main
  1. Recorded rate unavailable
    Latest
    Verified 2026-11-12
  2. Recorded rate unavailable
    Available · older version
    Verified 2026-10-20

Newest first. Release dates describe the model, not when today's rates took effect. Observations show when we recorded rates, not launch pricing. Image and text token meters are separate; no fixed image-token savings mix is assumed. How we verify

Availability and billing scope

OpenAI lists GPT-Realtime-2.1 as the current Realtime reasoning model for speech-to-speech interactions with tool use.

Official source

https://developers.openai.com/api/docs/pricing.md

Provider prices may change. This page uses the same structured record as our public dataset; the verification date belongs to this model, not the build date.

Download pricing data →