Google: Gemma 3 12B
google/gemma-3-12b-it
Cheapest provider
$0.04 / 1M
DeepInfra
Fastest provider (p95)
120 tok/s
SambaNova
Intelligence (composite)
59.6
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 |
|---|---|---|---|---|---|---|---|
| DeepInfra | full· bf16 | $0.0400 | $0.1300 | 332ms / 892ms | 15 / 51 tok/s | 100.00% | 100.0% |
| Cloudflare | undisclosed | $0.3450 | $0.5560 | 337ms / 831ms | 29 / 72 tok/s | 99.08% | 100.0% |
| SambaNova | undisclosed | $0.3500 | $0.5900 | 1006ms / 1748ms | 3 / 120.2 tok/s | 99.74% | 98.1% |
“—” 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 routes Google: Gemma 3 12B
- 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: Gemma 3 12B that’s currently DeepInfra at $0.04/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.