NEWMEN
← back to all models

DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2

DeepSeekopen-weight131K context12 providersIntelligence 83.3

Cheapest provider

$0.23 / 1M

StreamLake

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

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
StreamLakeundisclosed$0.2288$0.343299.17%
Baiduq8· fp8$0.2520$0.378099.77%
SiliconFlowq8· fp8$0.2590$0.420099.74%
AtlasCloudq8· fp8$0.2600$0.380099.48%
DeepInfraq4· fp4$0.2600$0.380098.49%
Novitaq8· fp8$0.2690$0.400099.92%
Parasailq8· fp8$0.2800$0.450098.34%
Alibabaundisclosed$0.3705$1.111599.79%
DigitalOceanundisclosed$0.4250$1.360099.83%
Friendliundisclosed$0.5000$1.500099.97%
Googleundisclosed$0.5600$1.680099.50%
SambaNovaundisclosed$3.0000$4.5000

“—” 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

  • Strict mode — pin DeepSeek: DeepSeek V3.2 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently StreamLake at $0.23/1M.
  • 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.