gpt-5.5 vs gpt-5.4-mini
gpt-5.5 vs gpt-5.4-mini: $5/$30 vs $0.75/$4.5 per 1M, the same workload priced on both; gpt-5.4-mini is 85% cheaper per request.
| gpt-5.5 | gpt-5.4-mini | |
|---|---|---|
| Provider · tier | openai · frontier | openai · fast |
| Input | $5 | $0.75 |
| Cached input | $0.5 | $0.075 |
| Cache write | none | none |
| Output | $30 | $4.5 |
| Long-context tier | > 272,000: $10 / $45 | none |
| Per request (2,000 in / 300 out) | $0.019 | $0.00285 |
| Per month at 100k requests | $1,900 | $285 |
| …with the static prefix cached | $1,225 | $184 |
| Cheaper sibling (cascade) | gpt-5.4-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-5.5 or gpt-5.4-mini?
At list prices (table 2026-10-26) gpt-5.4-mini is 85% 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.