NEWMEN
← back to all models

OpenAI: o4 Mini

openai/o4-mini

OpenAIclosed-weight200K context1 providerIntelligence 82.0

Cheapest provider

$1.10 / 1M

OpenAI

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (composite)

82.0

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime / price measured across providers over the last 30 minutes of live traffic. This is what proves “sourced cheapest” — Atlas mode draws on these per call to serve the cheapest path that holds quality.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
OpenAIfull· unknown$1.1000$4.4000100.00%

“—” means live telemetry hasn’t accumulated enough recent traffic for that endpoint. “undisclosed” means the provider serves the model but doesn’t expose the quantization label (typically running fp8 / int8 internally).

Intelligence breakdown

Composite score is a weighted average of public benchmarks (30% MMLU-Pro, 25% code pass@1, 25% math, 20% GPQA). Numbers come from model cards and the Artificial Analysis intelligence harness; missing components are renormalised over what’s present.

MMLU-Pro

81.9

broad reasoning

Code

71.8

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

92.7

math accuracy

GPQA Diamond

81.4

hard reasoning

Source: OpenAI o4-mini (MMLU-Pro 81.9, GPQA 81.4, LiveCodeBench v6 71.8, AIME25 92.7); Qwen3-235B-A22B-Thinking-2507 comparison table

How Atlas mode sources OpenAI: o4 Mini

  • Strict mode — pin OpenAI: o4 Mini exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently OpenAI at $1.10/1M.
  • Atlas mode — the default. Each call is auto-optimized for the cheapest path that holds quality, at least 5% off going direct from call one and climbing as it ramps. You always see which model served the call and exactly what you saved — thumbs-down anything you don’t like for a full refund.