Google: Gemini 2.5 Pro
google/gemini-2.5-pro
Cheapest provider
$1.25 / 1M
Fastest provider (p95)
148 tok/s
Google AI Studio
Intelligence (composite)
84.6
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 |
|---|---|---|---|---|---|---|---|
| full· unknown | $1.2500 | $10.0000 | 9932ms / 30083ms | 91 / 128 tok/s | 96.73% | 33.5% | |
| full· unknown | $1.2500 | $10.0000 | 9932ms / 30083ms | 91 / 128 tok/s | 61.36% | 33.5% | |
| full· unknown | $1.2500 | $10.0000 | 9932ms / 30083ms | 91 / 128 tok/s | 29.41% | 33.5% | |
| Google AI Studio | full· unknown | $1.2500 | $10.0000 | 3104ms / 18651ms | 105 / 148 tok/s | 85.40% | 90.5% |
“—” 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
86.0
broad reasoning
Code
80.0
pass@1 (HumanEval / LiveCodeBench)
AIME 2025
88.0
math accuracy
GPQA Diamond
84.0
hard reasoning
Source: Artificial Analysis (AA-aligned) — Gemini 2.5 Pro (MMLU-Pro 86, GPQA-D 84, LiveCodeBench 80, AIME25 88); github.com/MiniMax-AI/MiniMax-M2
How Atlas routes Google: Gemini 2.5 Pro
- 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 Google: Gemini 2.5 Pro that’s currently Google 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.