NEWMEN
← back to all models

DeepSeek: DeepSeek V3.2

deepseek/deepseek-v3.2

DeepSeekopen-weight131K context11 providersIntelligence 83.3

Cheapest provider

$0.25 / 1M

Baidu

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 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
Baiduq8· fp8$0.2520$0.378099.68%
StreamLakeundisclosed$0.2574$0.386199.35%
SiliconFlowq8· fp8$0.2590$0.420099.69%
AtlasCloudq8· fp8$0.2600$0.380096.21%
DeepInfraq4· fp4$0.2600$0.380099.99%
Novitaq8· fp8$0.2690$0.400099.74%
Parasailq8· fp8$0.2800$0.450095.93%
Alibabaundisclosed$0.3705$1.111598.81%
Friendliundisclosed$0.5000$1.500099.99%
Googleundisclosed$0.5600$1.680099.94%
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 routes DeepSeek: DeepSeek V3.2

  • 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 DeepSeek: DeepSeek V3.2 that’s currently Baidu at $0.25/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.