DeepSeek: DeepSeek V3.2 Exp
deepseek/deepseek-v3.2-exp
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| AtlasCloud | q8· fp8 | $0.2700 | $0.4100 | 1472ms / 3588ms | 4 / 32.6 tok/s | 97.96% | 98.4% |
| Novita | q8· fp8 | $0.2700 | $0.4100 | 1410ms / 3740ms | 16 / 41 tok/s | 99.05% | 99.0% |
| SiliconFlow | q8· fp8 | $0.2700 | $0.4100 | 2194ms / 6190ms | 17 / 25.2 tok/s | 98.29% | 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.