NEWMEN
← back to all models

DeepSeek: DeepSeek V3.2 Exp

deepseek/deepseek-v3.2-exp

DeepSeekopen-weight164K context3 providersIntelligence 83.3

Cheapest provider

$0.27 / 1M

AtlasCloud

Fastest provider (p95)

41 tok/s

Novita

Intelligence (composite)

83.3

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.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
AtlasCloudq8· fp8$0.2700$0.41001472ms / 3588ms4 / 32.6 tok/s97.96%98.4%
Novitaq8· fp8$0.2700$0.41001410ms / 3740ms16 / 41 tok/s99.05%99.0%
SiliconFlowq8· fp8$0.2700$0.41002194ms / 6190ms17 / 25.2 tok/s98.29%98.4%

“—” 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

85.0

broad reasoning

Code

79.0

pass@1 (HumanEval / LiveCodeBench)

AIME 2025

88.0

math accuracy

GPQA Diamond

80.0

hard reasoning

Source: Artificial Analysis (AA-aligned) via MiniMax-M2 table — DeepSeek-V3.2 (MMLU-Pro 85, GPQA-D 80, LiveCodeBench 79, AIME25 88); github.com/MiniMax-AI/MiniMax-M2

How Atlas mode sources DeepSeek: DeepSeek V3.2 Exp

  • Strict mode — pin DeepSeek: DeepSeek V3.2 Exp exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently AtlasCloud at $0.27/1M.
  • 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.