NEWMEN
← back to all models

DeepSeek: DeepSeek V4 Flash

deepseek/deepseek-v4-flash

DeepSeekopen-weight1.0M context13 providersIntelligence 75.0· est.

Cheapest provider

$0.10 / 1M

DeepInfra

Fastest provider (p95)

No throughput data yet — populated as traffic accumulates

Intelligence (estimated)

75.0

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
DeepInfraq4· fp4$0.1000$0.200099.50%
GMICloudq8· fp8$0.1120$0.224098.00%
Baiduq8· fp8$0.1260$0.252099.99%
Alibabaundisclosed$0.1340$0.268099.53%
Morphundisclosed$0.1390$0.278034.25%
AkashMLq8· fp8$0.1400$0.280099.85%
AtlasCloudq8· fp8$0.1400$0.280099.99%
DeepSeekundisclosed$0.1400$0.2800100.00%
Novitaq8· fp8$0.1400$0.280099.98%
Parasailq8· fp8$0.1400$0.280099.79%
SiliconFlowq8· fp8$0.1400$0.280097.68%
StreamLakeundisclosed$0.1540$0.308099.25%
Veniceundisclosed$0.1700$0.350099.89%

“—” 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 Flash

  • 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 Flash that’s currently DeepInfra at $0.10/1M.
  • Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.