Google: Gemini 2.5 Flash
google/gemini-2.5-flash
Cheapest provider
$0.30 / 1M
Fastest provider (p95)
184 tok/s
Intelligence (composite)
71.6
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| full· unknown | $0.3000 | $2.5000 | 2087ms / 9102ms | 89 / 184 tok/s | 97.88% | 95.1% | |
| full· unknown | $0.3000 | $2.5000 | 2087ms / 9102ms | 89 / 184 tok/s | 99.90% | 95.1% | |
| full· unknown | $0.3000 | $2.5000 | 2087ms / 9102ms | 89 / 184 tok/s | 95.13% | 95.1% | |
| Google AI Studio | full· unknown | $0.3000 | $2.5000 | 905ms / 7070ms | 40 / 177 tok/s | 99.92% | 99.9% |
“—” 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
—
broad reasoning
Code
62.3
pass@1 (HumanEval / LiveCodeBench)
AIME 2025
72.0
math accuracy
GPQA Diamond
82.8
hard reasoning
Source: Gemini 2.5 Flash Thinking (GPQA 82.8, LiveCodeBench 62.3, AIME25 72.0); DeepSeek-R1-0528 comparison table
How Atlas mode sources Google: Gemini 2.5 Flash
- Strict mode — pin Google: Gemini 2.5 Flash exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently Google at $0.30/1M.
- 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.