Meta: Llama 3.1 70B Instruct
meta-llama/llama-3.1-70b-instruct
Cheapest provider
$0.40 / 1M
DeepInfra
Fastest provider (p95)
83 tok/s
WandB
Intelligence (composite)
66.5
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q8· fp8 | $0.4000 | $0.4000 | 219ms / 840ms | 20 / 34 tok/s | 100.00% | 100.0% |
| DeepInfra | full· bf16 | $0.4000 | $0.4000 | 259ms / 713ms | 14 / 31 tok/s | 99.77% | 100.0% |
| Amazon Bedrock | undisclosed | $0.7200 | $0.7200 | 437ms / 707ms | 11 / 28 tok/s | 99.80% | 99.9% |
| WandB | full· bf16 | $0.8000 | $0.8000 | 207ms / 407ms | 25 / 83 tok/s | 100.00% | 100.0% |
“—” 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
66.5
broad reasoning
Code
80.8
pass@1 (HumanEval / LiveCodeBench)
MATH
68.1
math accuracy
GPQA Diamond
46.4
hard reasoning
Source: Meta Llama 3.1 model card (HumanEval / MATH / MMLU-Pro)
How Atlas routes Meta: Llama 3.1 70B Instruct
- 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 3.1 70B Instruct that’s currently DeepInfra at $0.40/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.