GPT Realtime 2.1 · aihubmix

GPT-Realtime-2.1 is a reasoning speech-to-speech model for the Realtime API, with tool use and configurable reasoning effort, improving on GPT-Realtime-2 in alphanumeric recognition, silence and noise handling, and interruption behavior.

Base model All models on this base All models of the provider to the provider

Input, $/1M $4.00

Output, $/1M $24.00

Cache read $0.40

Cache write —

Context 128 000

Max output 32 000

Accepts audio, images, text

Last checked 04.11.2026 12:00:14 UTC

Source provider's page

Price alerts

API

This model type has no common request format: see the provider's documentation.

API base URL	`https://aihubmix.com/api/v1`

Provider's API documentation

Source: AI Rate Card, https://airatecard.com/en/c/offer%3Aaihubmix%7Cgpt-realtime-2.1, prices checked 2026-11-04; seller's page: https://aihubmix.com

Technical details

ID: offer:aihubmix|gpt-realtime-2.1