Google: Gemma 3 12B
google/gemma-3-12b-it
Cheapest provider
$0.04 / 1M
DeepInfra
Fastest provider (p95)
218 tok/s
SambaNova
Intelligence (composite)
59.6
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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | full· bf16 | $0.0400 | $0.1300 | 505ms / 1752ms | 36 / 54 tok/s | 99.72% | 99.5% |
| SambaNova | undisclosed | $0.3500 | $0.5900 | 1074ms / 4639ms | 17 / 218 tok/s | 98.46% | 95.5% |
“—” 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
58.2
broad reasoning
Code
73.1
pass@1 (HumanEval / LiveCodeBench)
MATH
68.2
math accuracy
GPQA Diamond
34.1
hard reasoning
Source: Gemma 3 technical report
How Atlas mode sources Google: Gemma 3 12B
- Strict mode — pin Google: Gemma 3 12B exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.04/1M.
- 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.