O3 Mini

OpenAI

OpenAI's reasoning model at lower cost. Strong at math, coding, and science tasks.

Context Window: 200K tokens Released: 2025-01 Best For: Math, science, coding tasks requiring deep reasoning
  • Reasoning
  • Math optimization
  • Code generation
  • O3 Mini Pricing

    Token TypePrice per Million
    Input tokens$1.10
    Output tokens$4.40

    Estimated Cost by Project Size

    Realistic cost estimates for common coding scenarios. Assumes 30% cache hit rate where caching is available.

    ScenarioToken UsageEstimated Cost
    Small Script (1K lines) 50K input / 30K output $0.17
    Medium Feature (10K lines) 500K input / 200K output $1.27
    Large Project (50K lines) 2,500K input / 1,000K output $6.33
    Code Review (5K lines) 250K input / 25K output $0.30

    Benchmark Performance — O3 Mini

    Third-party benchmark scores normalized to 0-100 scale. Higher is better. Aggregated scores from published third-party benchmarks. SWE-bench measures real GitHub issue resolution. LiveCodeBench measures competitive programming ability. HumanEval measures basic code generation. BigCodeBench measures practical, multi-step coding tasks. All scores normalized to 0-100 scale.

    Overall Score 80/100
    SWE-bench Verified
    76
    LiveCodeBench
    85
    HumanEval
    94
    BigCodeBench
    65

    Sources: SWE-bench Verified, LiveCodeBench, HumanEval, BigCodeBench

    Get Access to O3 Mini

    Ready to start using O3 Mini? Get API access directly from OpenAI.

    Get API Access → Try O3 Mini Free →

    How Does O3 Mini Compare?

    ModelInput ($/M)Medium Feature Cost
    O3 Mini $1.10 $1.27 selected
    OpenAI o1-mini $1.10 $1.27 Compare
    OpenAI o4-mini $1.10 $1.27 Compare
    Claude Sonnet 4 Lite $1.00 $1.55 Compare
    Perplexity Sonar $1.00 $0.55 Compare
    Reka Core $1.00 $0.85 Compare

    Related Models

    Categories