OpenAI
gpt-4o-mini
Release date not recorded. Accessibility not recorded. Cheapest standard rate we hold: $0.60 per million output tokens, at long context.
What it costs
| Tier | Kind | In | Out | Cached in | From |
|---|---|---|---|---|---|
| batch | text · long | $0.07 | $0.30 | — | seller |
| batch | text · short | $0.07 | $0.30 | — | seller |
| fast | text · long | $0.25 | $1 | $0.13 | seller |
| fast | text · short | $0.25 | $1 | $0.13 | seller |
| standard | text · long | $0.15 | $0.60 | $0.07 | seller |
| standard | text · short | $0.15 | $0.60 | $0.07 | seller |
per million tokens, US dollars. * marks a rate from a single registry or two that disagree — the best available number rather than a confirmed one. Every other row is confirmed against a seller or a licensed index.
What it scores, by house
This model is not in Epoch's catalogue under a name we can match exactly, so we hold no scores for it. The match is exact after normalisation and never fuzzy, because a loose one would eventually price one model as another.
What retires, and when
- deprecation — 2026-05-07, replaced by gpt-realtime-mini
- deprecation — 2026-05-07, replaced by gpt-audio-mini
- deprecation — 2026-07-23
- deprecation — 2027-01-20, replaced by gpt-realtime-2.1-mini
- deprecation — 2027-01-20, replaced by gpt-4o-mini-transcribe-2025-12-15
- deprecation — 2027-01-20, replaced by gpt-audio-1.5
- deprecation — 2027-02-26, replaced by gpt-live-transcribe or gpt-transcribe
Every rate we hold · Why there is no single best model · Everything from OpenAI