GPT-5.4 mini
OpenAI's small-tier refresh for high-volume agents, positioned around tool-calling reliability at mini-tier prices across coding, science, and long-context work.
GPT-5.4 mini is available on MiniRouter as . The model page has current pricing, provider routes and API setup.
About the model
- Context: 400K. 128K maximum output per the announcement's spec table
- Reasoning effort: minimal – high. Four publisher-described effort levels; medium is the default
- Cached input: $0.04 / 1M. Discounted cached-input rate per the pricing table
- Weights: Not released. API-only; the announcement includes no weights
Publisher pricing
Pricing below comes from the linked publisher sources and does not represent a MiniRouter route or price.
| Phase | Input / 1M | Output / 1M | Blended / 1M | Effective | Source |
|---|---|---|---|---|---|
| Standard | $0.45 | $1.80 | $0.7875 | Aug 11, 2026 – open-ended | OpenAI ↗ |
Publisher-reported benchmarks
Results from the publisher’s announcement, grouped by unit.
| Benchmark | Reported result | Reported by | As of | Source |
|---|---|---|---|---|
| SWE-Bench Pro | 68.3% | OpenAI | Aug 11, 2026 | Announcement ↗ |
| Terminal Bench 2.1 | 81.7% | OpenAI | Aug 11, 2026 | Announcement ↗ |
| GPQA Diamond | 90.2% | OpenAI | Aug 11, 2026 | Announcement ↗ |
| DeepSWE v1.1 | 62.1% | OpenAI | Aug 11, 2026 | Announcement ↗ |
OpenAI reports the benchmark figures; MiniRouter has not reproduced them.
Independent measurements
Artificial Analysis evaluations of the first-party API.
GPT-5.4 mini (xhigh) ranks #86 of 462 model families on their Intelligence Index. Their headline uses the highest-scoring effort setting; every listed setting is below.
- Intelligence Index
- 24.1
- Composite of their evaluations
- Coding Index
- 56.1
- Coding evaluations only
- Blended price
- $1.69
- USD per 1M tokens, 3:1 input to output, first-party list
| Setting | Intelligence Index | Coding Index | Blended price |
|---|---|---|---|
| GPT-5.4 mini (xhigh) ↗ | 24.1 | 56.1 | $1.69 |
| GPT-5.4 mini (medium) ↗ | 19.7 | — | $1.69 |
| GPT-5.4 mini (non-reasoning) ↗ | 11.1 | — | $1.69 |
Source: Artificial Analysis ↗, read Sep 21, 2026. Measured on the model's first-party API, not a MiniRouter route.
Keep exploring
Compare published results in the model rankings and coding benchmarks, or read more model releases.
For MiniRouter product updates, visit the changelog.
Sources
- Read at OpenAI ↗
OpenAI announcement
Published Aug 11, 2026
- Read at Artificial Analysis ↗
Artificial Analysis model page
Published Sep 21, 2026
Editorial reference revised 2026-10-07. Catalog status comes from the generated routing snapshot.