DeepSeek: DeepSeek V4 Pro
deepseek/deepseek-v4-pro
Cheapest provider
$0.43 / 1M
DeepSeek
Fastest provider (p95)
—
No throughput data yet — populated as traffic accumulates
Intelligence (composite)
90.2
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 |
|---|---|---|---|---|---|---|---|
| DeepSeek | undisclosed | $0.4350 | $0.8700 | — | — | 99.99% | — |
| Baidu | q8· fp8 | $0.7605 | $1.5210 | — | — | 98.92% | — |
| DeepInfra | q4· fp4 | $1.3000 | $2.6000 | — | — | 99.45% | — |
| GMICloud | q8· fp8 | $1.3920 | $2.7840 | — | — | 98.26% | — |
| StreamLake | undisclosed | $1.5660 | $3.1320 | — | — | 98.58% | — |
| Novita | q8· fp8 | $1.6000 | $3.2000 | — | — | 99.70% | — |
| SiliconFlow | q8· fp8 | $1.6000 | $3.4800 | — | — | 99.55% | — |
| Alibaba | undisclosed | $1.6080 | $3.2160 | — | — | 97.53% | — |
| AtlasCloud | q8· fp8 | $1.6800 | $3.3800 | — | — | 97.86% | — |
| Venice | undisclosed | $1.7300 | $3.7960 | — | — | 96.74% | — |
| DigitalOcean | undisclosed | $1.7400 | $3.4800 | — | — | 97.89% | — |
| Fireworks | undisclosed | $1.7400 | $3.4800 | — | — | 96.87% | — |
| Parasail | q8· fp8 | $1.7400 | $3.4800 | — | — | 96.12% | — |
| Together | undisclosed | $2.1000 | $4.4000 | — | — | 91.42% | — |
“—” 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
87.5
broad reasoning
Code
93.5
pass@1 (HumanEval / LiveCodeBench)
MATH
—
math accuracy
GPQA Diamond
90.1
hard reasoning
Source: DeepSeek V4-Pro Max (MMLU-Pro 87.5, GPQA-Diamond 90.1, LiveCodeBench 93.5); framia / morphllm benchmark tables + Artificial Analysis Intelligence Index ~52
How Atlas mode sources DeepSeek: DeepSeek V4 Pro
- Strict mode — pin DeepSeek: DeepSeek V4 Pro exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepSeek at $0.43/1M.
- 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.