Skip to main content

OpenAIAudio modelActive

GPT-Realtime 2.1 Mini

PopularityRank 670 of 875

0out of 100same as last month

Summary

GPT-Realtime 2.1 Mini is OpenAI’s real-time model for audio and voice conversations. It accepts audio, text, and images, returns audio and text, and has a 128,000-token context with up to 32,000 output tokens.

OpenAI released it on July 6, 2026. Per 1 million input tokens, text costs $0.60, cached text $0.06, audio $10, cached audio $0.30, images $0.80, and cached images $0.08; per 1 million output tokens, text costs $2.40 and audio $20.

Popularity compared

How often the model is searched for, used and mentioned, compared with every model of its category.

Popularity index

0 to 100, higher is more popular

20 of 83 models

pyannote Community-173
Nemotron-3-Diarization57
Gemini 3.5 Transcribe52
Confucius4-R2T252
Granite Speech 5.0 470M TurboCTC52
Kokoro-82M51
Nova-351
Fish Audio S2 Pro51
NVIDIA Nemotron 3.5 Transcribe50
Granite Speech 5.0 470M TurboCTC NC50
Orukeet49
Lyria 3.547
Gemini 3.5 Live Translate46
Phonon-244
Aura-244
Gemini 3.1 Flash TTS44
MiniMax-Music341
Audio8-ASR-Infinite41
GPT-Realtime 2.141
GPT-Realtime 2.1 Mini0

As of November 2026 · Source: gradually.ai popularity index

Over time

Weekly values from November 1, 2026 to November 5, 2026

GPT-Realtime 2.1 MiniAmazon Nova 2 SonicEleven Multilingual STS v2Eleven Music v2.5Eleven Text to Sound v2

All specifications

Architecture

Model class
Real-time audio model
Source: Model class
Knowledge cutoff
Sep 30, 2024
Source: Knowledge cutoff

Input and output

Input
Audio, image and text
Source: Input
Output
Audio and text
Source: Output
Context window
128,000 tokens
Source: Context window
Maximum output
32,000 tokens
Source: Maximum output

Watermarking and provenance

AI watermarking refers to invisible signals embedded in the output. Visible marks and provenance metadata are listed separately. Unknown means there is insufficient evidence for that particular field.

AI watermarking
Subject to limitations. OpenAI lists an inaudible SynthID watermark for supported audio outputs through ChatGPT and the OpenAI API. Coverage can depend on the model, output path and creation date.
Source: AI watermarking
Watermarking technique
SynthID
Source: Watermarking technique
Labelling reviewed
Nov 5, 2026
Source: Labelling reviewed

Licence and access

Access
API
Source: Access

API

API model ID
gpt-realtime-2.1-mini
Source: API model ID

Further details

Task
Voice dialogue
Source: Task
Supported details
Real-time voice dialogue with tool use
Source: Supported details

Prices

Text input price
$0.60 per 1M text tokensSource
Cached text input price
$0.06 per 1M cached text tokensSource
Text output price
$2.40 per 1M text tokensSource
Audio input price
$10 per 1M audio tokensSource
Cached audio input price
$0.30 per 1M cached audio tokensSource
Audio output price
$20 per 1M audio tokensSource
Image input price
$0.80 per 1M image tokensSource
Cached image input price
$0.08 per 1M cached image tokensSource

Sources and data date

Show all 10 sources
TypeEvidence and data date
Additional sourceOpenAI model documentation (retrieved October 25, 2026) · OpenAI GPT-Realtime 2.1 Mini model documentation · Editorial description reviewed October 25, 2026
Additional sourceOpenAI API changelog (retrieved October 25, 2026) · OpenAI API changelog · Editorial description reviewed October 25, 2026
Additional sourceOfficial API pricing (retrieved October 25, 2026) · OpenAI API pricing · Editorial description reviewed October 25, 2026
Additional sourceOpenAI: Provenance signals (retrieved November 5, 2026)
Additional sourceOpenRouter: Popularity index (derived), CC BY 4.0
Additional sourceVercel AI Gateway: Popularity index (derived), CC BY 4.0
Additional sourceOllama: cumulative downloads for the popularity index
Additional sourceReplicate: cumulative runs for the popularity index
Additional sourceGoogle Trending Now: limited feed selection for Germany and the US
Additional sourceCreative Commons Attribution 4.0