DeepSeek: DeepSeek V3.1
deepseek/deepseek-chat-v3.1
Cheapest provider
$0.21 / 1M
DeepInfra
Fastest provider (p95)
158 tok/s
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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q4· fp4 | $0.2100 | $0.7900 | 810ms / 2456ms | 11 / 15 tok/s | 99.73% | 85.8% |
| Novita | q8· fp8 | $0.2700 | $1.0000 | 1746ms / 4343ms | 17 / 35 tok/s | 100.00% | 100.0% |
| SiliconFlow | q8· fp8 | $0.2700 | $1.0000 | 1305ms / 5678ms | 16 / 24 tok/s | 95.04% | 95.1% |
| AtlasCloud | q8· fp8 | $0.3000 | $0.9500 | 1573ms / 3991ms | 6 / 22 tok/s | 99.43% | 99.4% |
| WandB | q8· fp8 | $0.5500 | $1.6500 | 349ms / 681ms | 27 / 42 tok/s | 99.99% | 100.0% |
| undisclosed | $0.6000 | $1.7000 | 694ms / 1520ms | 55 / 158 tok/s | 99.39% | 86.7% | |
| SambaNova | q8· fp8 | $0.6500 | $1.5000 | 1195ms / 5184ms | 57 / 155 tok/s | 98.38% | 72.8% |
“—” 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 mode sources DeepSeek: DeepSeek V3.1
- Strict mode — pin DeepSeek: DeepSeek V3.1 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.21/1M.
- 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.