NEWMEN
← back to all models

OpenAI: GPT-5

openai/gpt-5

OpenAIclosed-weight400K context3 providersIntelligence 87.8

Cheapest provider

$1.25 / 1M

Azure

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (composite)

87.8

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$1.2500$10.0000
Azurefull· unknown$1.2500$10.0000
OpenAIfull· unknown$1.2500$10.000099.92%

“—” 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

87.0

broad reasoning

Code

85.0

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

94.0

math accuracy

GPQA Diamond

85.0

hard reasoning

Source: Artificial Analysis (AA-aligned) — GPT-5 thinking (MMLU-Pro 87, GPQA-D 85, LiveCodeBench 85, AIME25 94); via MiniMax-M2 table + GPT-5 system card

How Atlas routes OpenAI: GPT-5

  • 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-5 that’s currently Azure at $1.25/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.