NEWMEN
← back to all models

Meta: Llama 4 Scout

meta-llama/llama-4-scout

Metaopen-weight10M context4 providersIntelligence 54.5

Cheapest provider

$0.08 / 1M

DeepInfra

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (composite)

54.5

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$0.300099.99%
Groqundisclosed$0.1100$0.340099.91%
Novitafull· bf16$0.1800$0.5900100.00%
Googleundisclosed$0.2500$0.7000100.00%

“—” 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

74.3

broad reasoning

Code

32.8

pass@1 (HumanEval / LiveCodeBench)

MATH

50.3

math accuracy

GPQA Diamond

57.2

hard reasoning

Source: Meta Llama 4 model card — Scout instruct (MMLU-Pro 74.3, GPQA-Diamond 57.2, LiveCodeBench 32.8, MATH 50.3); llama.com/models/llama-4

How Atlas routes Meta: Llama 4 Scout

  • 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 Meta: Llama 4 Scout 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.