OpenAI: GPT-4o
openai/gpt-4o
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| Azure | full· unknown | $2.5000 | $10.0000 | 1031ms / 3296ms | 39 / 141 tok/s | 99.74% | 66.3% |
| OpenAI | full· unknown | $2.5000 | $10.0000 | 679ms / 2220ms | 45 / 98 tok/s | 99.41% | 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.