NEWMEN
← back to all models

DeepSeek: DeepSeek V4 Pro

deepseek/deepseek-v4-pro

DeepSeekopen-weight1.0M context13 providersIntelligence 74.2· est.

Cheapest provider

$0.43 / 1M

DeepSeek

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

74.2

Family + generation + popularity + price tier

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
DeepSeekundisclosed$0.4350$0.870099.99%
DeepInfraq4· fp4$1.3000$2.600098.87%
GMICloudq8· fp8$1.3920$2.784099.03%
Baiduq8· fp8$1.5210$3.042099.96%
Novitaq8· fp8$1.6000$3.380099.94%
Alibabaundisclosed$1.6080$3.216099.59%
SiliconFlowq8· fp8$1.6200$3.480098.70%
StreamLakeundisclosed$1.6530$3.306097.43%
AtlasCloudq8· fp8$1.6800$3.380098.86%
Veniceundisclosed$1.7300$3.796099.41%
Fireworksundisclosed$1.7400$3.480091.53%
Parasailq8· fp8$1.7400$3.480099.46%
Togetherundisclosed$2.1000$4.400096.33%

“—” 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 estimate

No public benchmark numbers indexed for this model yet, so the leaderboard score is derived from the catalogue data we sync: model family standing, generation, and live usage rank — applied identically to open- and closed-weight models. The heuristic ceiling sits below confirmed-benchmark frontier models so curated rankings stay clearly on top.

Want a curated score? File a benchmark report and we’ll add it to the next sync.

How Atlas routes DeepSeek: DeepSeek V4 Pro

  • 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 V4 Pro that’s currently DeepSeek at $0.43/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.