gpt-4o vs gpt-4o-mini
gpt-4o vs gpt-4o-mini: $2.5/$10 vs $0.15/$0.6 per 1M, the same workload priced on both; gpt-4o-mini is 94% cheaper per request.
| gpt-4o | gpt-4o-mini | |
|---|---|---|
| Provider · tier | openai · mid | openai · fast |
| Input | $2.5 | $0.15 |
| Cached input | $1.25 | $0.075 |
| Cache write | none | none |
| Output | $10 | $0.6 |
| Long-context tier | none | none |
| Per request (2,000 in / 300 out) | $0.008 | $0.00047999999999999996 |
| Per month at 100k requests | $800 | $48 |
| …with the static prefix cached | $613 | $37 |
| Cheaper sibling (cascade) | gpt-4o-mini | — |
Through TokenZero
Point your SDK at the gateway and keep both keys; the cache formatter, response cache and advisory routing act on every request, and each one comes back with a signed receipt showing the list-price baseline, actual cost and the saving.
OPENAI_BASE_URL=https://tokenzero.sh/w/<key>/v1 ANTHROPIC_BASE_URL=https://tokenzero.sh/w/<key>
Questions
Which is cheaper, gpt-4o or gpt-4o-mini?
At list prices (table 2026-10-26) gpt-4o-mini is 94% cheaper per request on a 2,000-in / 300-out workload. Quality is a separate question: TokenZero's cascade only routes to a sibling it scores as sufficient and measures parity with shadow evaluation.
Where do these prices come from?
The providers' own pricing pages, re-verified on 2026-10-26; the gateway signs receipts with the same table.