O3 Mini

by OpenAI

Reasoning model with adjustable thinking. Use reasoning_effort low/medium/high. No temperature support.

ReasoningToolsStructured output
Context window
200K
Max output
100K
Input price
$1.10 /1M
Output price
$4.40 /1M

Benchmarks

Independent benchmark scores — composite indices for reasoning, coding, and math, plus individual eval scores where available.

Global rank#183 of 505 LLMs
TierEfficient
Output speed126 tok/s
First token8.19s
Intelligence Index25.9
Coding Index17.9
MMLU-Pro
79%
GPQA Diamond
75%
Humanity's Last Exam
9%
LiveCodeBench
72%
SciCode
40%
Terminal-Bench Hard
7%
τ²-Bench Telecom
29%

Available routes

The same O3 Mini runs on 1 route through the Opper gateway. Each route has its own data-handling posture.

ProviderRegionZero data retentionTrainingLoggingContractInputOutput
OpenAIUSOpt-inNo (opt-in)
Up to 30 days for abuse monitoring on stateless endpoints. Stateful endpoints (Conversations, ChatKit, Vector Stores) retain until deleted.
Enterprise$1.10$4.40

Human review: Abuse-flagged only

Other models from OpenAI

Start building with 300+ models

One API key. Every major provider. Up and running in minutes.

Get startedView Documentation
O3 Mini by OpenAI — pricing, benchmarks, hosting routes | Opper AI