NEWMEN
← back to all models

Google: Gemma 3 27B

google/gemma-3-27b-it

Googleopen-weight131K context5 providersIntelligence 66.3

Cheapest provider

$0.08 / 1M

DeepInfra

Fastest provider (p95)

63 tok/s

Phala

Intelligence (composite)

66.3

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.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
DeepInfraq8· fp8$0.0800$0.1600908ms / 3972ms18 / 28 tok/s97.94%97.2%
Parasailq8· fp8$0.0800$0.4500984ms / 3131ms31 / 54 tok/s99.91%99.2%
Nebiusq8· fp8$0.1000$0.3000643ms / 1851ms17 / 54 tok/s97.51%99.5%
Phalaundisclosed$0.1100$0.4000744ms / 1837ms34 / 63 tok/s100.00%61.1%
Novitafull· bf16$0.1190$0.2000990ms / 38881ms18 / 29 tok/s71.89%90.2%

“—” 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

64.3

broad reasoning

Code

79.2

pass@1 (HumanEval / LiveCodeBench)

MATH

75.2

math accuracy

GPQA Diamond

41.8

hard reasoning

Source: Gemma 3 technical report

How Atlas routes Google: Gemma 3 27B

  • 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 27B that’s currently DeepInfra at $0.08/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.