NEWMEN
← back to all models

DeepSeek: DeepSeek V3.1 Terminus

deepseek/deepseek-v3.1-terminus

DeepSeekopen-weight164K context4 providersIntelligence 71.0· est.

Cheapest provider

$0.27 / 1M

DeepInfra

Fastest provider (p95)

41 tok/s

DeepInfra

Intelligence (estimated)

71.0

Family + generation + popularity + price tier

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.

ProviderQuantInput $/1MOutput $/1MLatency p50 / p95Throughput p50 / p95Uptime 30mSuccess
DeepInfraq4· fp4$0.2700$0.95001034ms / 5557ms19 / 41 tok/s99.42%99.3%
Novitaq8· fp8$0.2700$1.00001687ms / 2457ms23 / 34 tok/s100.00%100.0%
SiliconFlowq8· fp8$0.2700$1.00001387ms / 4552ms21 / 26 tok/s96.26%96.1%
AtlasCloudq8· fp8$0.3000$0.95001489ms / 4828ms13 / 24.3 tok/s100.00%100.0%

“—” 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 mode sources DeepSeek: DeepSeek V3.1 Terminus

  • Strict mode — pin DeepSeek: DeepSeek V3.1 Terminus exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra 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.