DeepSeek: DeepSeek V3.1
deepseek/deepseek-chat-v3.1
Cheapest provider
$0.21 / 1M
DeepInfra
Fastest provider (p95)
157 tok/s
SambaNova
Intelligence (estimated)
71.0
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q4· fp4 | $0.2100 | $0.7900 | 854ms / 2781ms | 11 / 18 tok/s | 99.79% | 58.9% |
| Novita | q8· fp8 | $0.2700 | $1.0000 | 1766ms / 3854ms | 21 / 35 tok/s | 100.00% | 100.0% |
| SiliconFlow | q8· fp8 | $0.2700 | $1.0000 | 1374ms / 7194ms | 16 / 23 tok/s | 98.93% | 93.9% |
| AtlasCloud | q8· fp8 | $0.3000 | $0.9500 | 1521ms / 3234ms | 20 / 31 tok/s | 99.93% | 100.0% |
| WandB | q8· fp8 | $0.5500 | $1.6500 | 318ms / 612ms | 33 / 49 tok/s | 99.98% | 100.0% |
| undisclosed | $0.6000 | $1.7000 | 756ms / 1796ms | 63 / 98 tok/s | 99.95% | 93.7% | |
| SambaNova | q8· fp8 | $0.6500 | $1.5000 | 1119ms / 5982ms | 58 / 157 tok/s | 99.35% | 80.6% |
“—” 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.
- ·deepseek v family base
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes DeepSeek: DeepSeek V3.1
- 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 V3.1 that’s currently DeepInfra at $0.21/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.