OpenAI · Frontier
o4-mini
A closed model, reached through gm. The route is sealed in transit and in use; the model maker still receives the prompt under its API terms.
- Tool calling: yes
- Image input: yes
Released
Apr 2025Knowledge cutoff
Jun 2024Modalities
Text · Tool calling · Image inputBest price on gm
-31.3%In
Cached
Out
per Mtok*
Recent effective price
What buyers have actually paid on this model recently, across every provider and cache hits.
Input
$0.82
$1.10Cached input
$0.205
$0.275Output
$3.28
$4.40How the effective price is calculated
Requests are load balanced across every provider serving this model, each offering its own rate, so what you pay is a blend rather than a single number. These are the blended rates actually paid — priced at what a provider offered, capped at list.
Measured over 9 windows: 1,497 requests and 2,261,347 input-side tokens. Most recent window closed 2026-08-11 02:24 UTC.
Who's serving this model
Every provider currently serving this model, ranked by discount.
| Provider | Discount | In | Out |
|---|---|---|---|
| Provider 1 | 31.3% off | $0.76 | $3.02 |
| Provider 2 | 29.3% off | $0.78 | $3.11 |
| Provider 3 | — | $1.10 | $4.40 |
| Provider 4 | — | $1.10 | $4.40 |
Performance
Measured on the requests gm routed to this model.
- Throughput
- 129.2 tok/sover 2,049 requests
- Time to first token
- 4.1 sover 2,050 requests
- Request success rate
- 100.0% over 2,050 requests
Benchmarks
Fixed-seed suites gm runs against this model.