DeepSeek: DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
Cheapest provider
$0.20 / 1M
DeepInfra
Fastest provider (p95)
76 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.
| Provider | Quant | Input $/1M | Output $/1M | Latency p50 / p95 | Throughput p50 / p95 | Uptime 30m | Success |
|---|---|---|---|---|---|---|---|
| DeepInfra | q4· fp4 | $0.2000 | $0.7700 | 420ms / 1319ms | 34 / 76 tok/s | 98.43% | 99.7% |
| AtlasCloud | q8· fp8 | $0.2160 | $0.8800 | 1470ms / 3799ms | 5 / 16 tok/s | 99.43% | 99.5% |
| ModelRun | q4· fp4 | $0.2200 | $0.8000 | 1201ms / 3767ms | 35 / 49 tok/s | 99.81% | 98.9% |
| SiliconFlow | q8· fp8 | $0.2500 | $1.0000 | 1482ms / 3829ms | 18 / 27 tok/s | 98.23% | 98.6% |
| Novita | q8· fp8 | $0.2700 | $1.1200 | 1386ms / 3685ms | 23 / 31 tok/s | 99.07% | 99.0% |
| GMICloud | q8· fp8 | $0.2900 | $1.1400 | 2698ms / 6040ms | 17 / 31 tok/s | 98.95% | 98.6% |
“—” 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 mode sources DeepSeek: DeepSeek V3 0324
- Strict mode — pin DeepSeek: DeepSeek V3 0324 exactly and we pass it straight through, sourced from the cheapest provider above. The same model, no substitutions — currently DeepInfra at $0.20/1M.
- 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.