Back to models
available

GPT-Realtime-2.1

openai/gpt-realtime-2-1

Prices

Input

$4.00 per 1M tokens

medium
Input (audio tokens)

$0.40 per 1M tokens

low
Input (audio, cached read)

$0.40 per 1M tokens

low
Input (audio)

$32.00 per 1M tokens

medium
Input (cached read)

$0.40 per 1M tokens

medium
Input (cached read) (modality: audio)

$0.40 per 1M tokens

medium
Input (cached read) (modality: image)

$0.50 per 1M tokens

medium
Input (cached read) (modality: text)

$0.40 per 1M tokens

medium
Input (image tokens)

$5.00 per 1M tokens

low
Input (modality: audio)

$32.00 per 1M tokens

medium
Input (modality: image)

$5.00 per 1M tokens

medium
Input (modality: text)

$4.00 per 1M tokens

medium
Output

$24.00 per 1M tokens

medium
Output (audio)

$64.00 per 1M tokens

medium
Output (modality: audio)

$64.00 per 1M tokens

medium
Output (modality: text)

$24.00 per 1M tokens

medium

Also available on

The same model, sold by someone else. The price above is the maker's own.

2 sales channels for this model.
ChannelWhatPrice
Microsoft AzureInput$4.00 per 1M tokens
Input (audio tokens)$0.40 per 1M tokens
Input (audio, cached read)$0.40 per 1M tokens
Input (audio)$32.00 per 1M tokens
Input (cached read)$0.40 per 1M tokens
Input (image tokens)$5.00 per 1M tokens
Output$24.00 per 1M tokens
Output (audio)$64.00 per 1M tokens
Other · vercelInput$4.00 per 1M tokens
Input (cached read)$0.40 per 1M tokens
Output$24.00 per 1M tokens

Specifications

Provider
openai
Context window
128,000
Max output tokens
32,000
Open weights
no
Released
07/06/2026
Retires
07/31/2027
First seen by this tracker

Price history

No price of this model has changed since we started tracking it.

Input (modality: audio)
32 per 1M tokens, unchanged since 09/14/2026
Input (cached read) (modality: audio)
0.4 per 1M tokens, unchanged since 09/14/2026
Output (modality: audio)
64 per 1M tokens, unchanged since 09/14/2026
Input (modality: text)
4 per 1M tokens, unchanged since 09/14/2026
Input (cached read) (modality: text)
0.4 per 1M tokens, unchanged since 09/14/2026
Output (modality: text)
24 per 1M tokens, unchanged since 09/14/2026
Input (modality: image)
5 per 1M tokens, unchanged since 09/14/2026
Input (cached read) (modality: image)
0.5 per 1M tokens, unchanged since 09/14/2026
Input
4 per 1M tokens, unchanged since 09/14/2026
Output
24 per 1M tokens, unchanged since 09/14/2026
Input (cached read)
0.4 per 1M tokens, unchanged since 09/14/2026
Input (audio)
32 per 1M tokens, unchanged since 09/14/2026
Output (audio)
64 per 1M tokens, unchanged since 09/14/2026
Input (audio tokens)
0.4 per 1M tokens, unchanged since 09/14/2026
Input (audio, cached read)
0.4 per 1M tokens, unchanged since 09/14/2026
Input (image tokens)
5 per 1M tokens, unchanged since 09/14/2026

Last updated 10/03/2026, 02:10