o3 Mini High
OpenAI released 2025-02-12
GPT-5.6 Luna is both better and cheaper.
It scores +36.6 higher and costs 77% less ($0.450/M against $1.93/M) on this workload — and it does everything this model does.
Gemini 3.7 Flash is cheaper still (61% less) but drops 100K → 66K max output.
The same model via batch is 50% cheaper ($0.963/M) — same weights, different latency.
Every price dimension
| Input | $1.10/M |
|---|---|
| Output | $4.40/M |
| Cached input | $0.550/M |
| Web search | $0.01/call |
Independent scores
| Intelligence | 15.7 |
|---|---|
| Coding | 16.3 |
| Agentic | 1.7 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 200K |
|---|---|
| Max output | 100K |
| Input modes | text, file |
| Tool use | yes |
| Reasoning | always on |
| Knowledge cutoff | 2023-10-31 |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
OpenAI o3-mini-high is the same model as [o3-mini](/openai/o3-mini) with reasoning_effort set to high. o3-mini is a cost-efficient language model optimized for STEM reasoning tasks, particularly excelling in science, mathematics, and...