Fresh paint, wet floors — we're rebuilding CostOfToken into a cross-provider price comparison. Some corners are still under construction; the full version is coming up soon.

gpt-realtime pricing

gpt-realtime from OpenAI costs $4.00 per 1M input tokens and $16.00 per 1M output tokens. Cached input is $0.400 per 1M.

API id gpt-realtime · OpenAI · source · updated 2026-09-25

We have not confirmed what kind of model this is. Its name suggests one thing and its pricing another, and we would rather say so than guess.

$4.00
Input / 1M tokens
$16.00
Output / 1M tokens
$0.400
Cached input / 1M
—
Context window

gpt-realtime specifications

Provider
OpenAI
API id
gpt-realtime
Model type
unknown
Context window
— tokens
Max output
not published
Currency
USD
Price source
First-party
Last checked
2026-09-25

Tags

  • audio

What gpt-realtime costs in practice

Estimated cost at common usage volumes
WorkloadInput tokensOutput tokensEstimated cost
Short chat turn1,000500$0.01
Document summary50,0002,000$0.23
1M tokens in, 200K out1,000,000200,000$7.20

Estimates use the standard tier and ignore caching discounts, so real bills with repeated prompt prefixes are typically lower.

gpt-realtime price history

RecordedInput /1MOutput /1M
2026-08-25$4.00$16.00
2026-08-23$32.00—
2026-08-22$4.00—

Common questions

How much does gpt-realtime cost per 1M tokens?
gpt-realtime costs $4.00 per 1M input tokens and $16.00 per 1M output tokens on the standard tier. Cached input is $0.400 per 1M.
What is gpt-realtime's context window?
OpenAI does not publish a context window for gpt-realtime on its pricing page.
Is there a cheaper OpenAI model than gpt-realtime?
Yes. omni-moderation-latest is free per 1M input tokens versus $4.00 for gpt-realtime.
Where does this gpt-realtime price come from?
Directly from OpenAI's published pricing page, re-read every day and normalized to USD per 1,000,000 tokens.

Head-to-head comparisons

Other OpenAI models

See all OpenAI pricing →