ModelPriceWatch.com
Last scan 2026-09-23 Models tracked 270 Providers 35 Cheapest paid Granite 4.0 H Micro $0.017/Mtok in Every price links to its source

GPT-Realtime-2

by OpenAI

Current flagship mid tier
Availability: OpenAI released the newer GPT-Realtime-2.1 on 2026-07-06, but it did not retire this model: GPT-Realtime-2 is still on OpenAI's rate card at the same prices, still listed in its model index, and it appears in none of the shutdown tables on OpenAI's deprecations page. The two generations are sold side by side at identical text and audio rates, so this row is current rather than superseded.

Today's price · per 1M tokens

Input

$4.00

per 1M tokens

Output

$24.00

per 1M tokens

Blended

$9.00

blended $/1M — 3:1 weighted input:output

Cached input

$0.400

10% of input — prompt caching

How this price is scoped: OpenAI prices this model per 1M tokens on three separate modalities: text at $4.00 input / $0.40 cached input / $24.00 output, audio at $32.00 / $0.40 / $64.00, and image input at $5.00 / $0.50. The tracked figures are the TEXT rates.

Source: official OpenAI pricing · read MODELPRICEWATCH.COM · 2026-09-23

Price receipt

We read OpenAI's own pricing page on and found gpt-realtime-2 listed with a price on the same row — that read is where the number above comes from. We keep the page text we read; its content hash is fdefe4c05a.

Overview

Realtime voice and audio model. Text tokens $4/$24 per 1M; audio tokens $32/$64 per 1M.

Capabilities

struck through = not supported
Input 2/4
Text Image Audio Video
Output
Text
Features 4/9
Prompt caching Reasoning Coding Fast inference Long context Open weights Multimodal Web search Realtime

Specifications

Provider
OpenAI
Context window
128K tokens
Modality
audio, text
Parameters
Proprietary
Open source
No — proprietary
Released
Status
Current
Last updated
Tags
realtimeaudioflagship

Availability verified: listed on OpenAI's own page