NEWMEN
← back to all models

OpenAI: GPT-4o

openai/gpt-4o

OpenAIclosed-weight128K context2 providersIntelligence 74.5

Cheapest provider

$2.50 / 1M

Azure

Fastest provider (p95)

141 tok/s

Azure

Intelligence (composite)

74.5

MMLU-Pro · HumanEval · math · GPQA

Per-provider performance

Latency / throughput / uptime measured across providers over the last 30 minutes of live traffic. Atlas’s router weighs these per call (with the eval-gate signal) when picking a variant for Standard and Batch tiers.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
Azurefull· unknown$2.5000$10.00001031ms / 3296ms39 / 141 tok/s99.74%66.3%
OpenAIfull· unknown$2.5000$10.0000679ms / 2220ms45 / 98 tok/s99.41%99.7%

“—” 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

73.6

broad reasoning

Code

90.2

pass@1 (HumanEval / LiveCodeBench)

MATH

76.2

math accuracy

GPQA Diamond

53.9

hard reasoning

Source: OpenAI GPT-4o System Card (Aug 2024)

How Atlas routes OpenAI: GPT-4o

  • Realtime tier — direct passthrough at the upstream’s native precision. Best for hard latency / quality guarantees.
  • Standard tier — Atlas picks the cheapest provider variant whose quantization has stayed green on your operation’s eval gates. For OpenAI: GPT-4o that’s currently Azure at $2.50/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.