o3 Mini High
by OpenAI · openai/o3-mini-high · #225 cheapest of 325 paid models
Prices updated Jul 22, 2026, 1:40 AM UTC · refreshed hourly
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...
Compare vs:Claude Sonnet 5Claude Opus 4.6Claude Haiku 4.5Gemini 3.6 Flash
Pricing
Input
$1.10
per 1M tokens
Output
$4.40
per 1M tokens
Blended (3:1)
$1.93
3 input : 1 output
Cache read
$0.55
per 1M cached tokens
Cache write
—
per 1M tokens
Cache & batch economics
Effective prices for o3 Mini High with prompt caching.
| Cache hit rate | Effective blended $/1M | Example request* | vs no cache |
|---|---|---|---|
| 0% | $1.93 | $0.1166 | — |
| 50% | $1.72 | $0.0891 | −24% |
| 90% | $1.55 | $0.0671 | −42% |
*Example: 100K sticky context + 2K new input + 1K output. Batch discount is an approximate 50% off list rates for this provider’s batch API. Confirm on the vendor’s pricing page.
What a request costs
| Workload | Input tokens | Output tokens | Cost / request | Cost / 1K requests |
|---|---|---|---|---|
| Short chat message | 500 | 300 | $0.00187 | $1.87 |
| Document summary | 8,000 | 1,000 | $0.0132 | $13.20 |
| Codebase question (RAG) | 30,000 | 2,000 | $0.0418 | $41.80 |
| Long-context analysis | 150,000 | 5,000 | $0.187 | $187.00 |
Performance
Intelligence Index
15.6
AA composite quality
Coding Index
16.3
Math Index
—
Agentic Index
1.7
Output speed
240 tok/s
median
Time to first token
14.70s
median
Time to first answer
14.70s
after reasoning tokens
Artificial Analysis benchmarks
| Benchmark | Score |
|---|---|
| MMLU-Pro | 80.2% |
| GPQA Diamond | 77.3% |
| Humanity's Last Exam | 12.3% |
| LiveCodeBench | 73.4% |
| SciCode | 39.8% |
| MATH-500 | 98.5% |
| AIME | 86.0% |
| IFBench | 67.1% |
| AA-LCR (Long Context Reasoning) | 39.3% |
| Terminal-Bench Hard | 6.1% |
| Terminal-Bench 2.1 | 4.5% |
| τ²-Bench (Telecom) | 31.3% |
| τ³-Bench Banking | 5.2% |
Specs
Context window
200K
tokens
Max output
100K
tokens
Input modalities
text, file
Tokenizer
GPT