DeepSeek: DeepSeek V3 0324
deepseek/deepseek-chat-v3-0324
Cheapest provider
$0.20 / 1M
DeepInfra
Fastest provider (p95)
46 tok/s
ModelRun
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 | $0.2000 | $0.7700 | 805ms / 6927ms | 12 / 24 tok/s | 88.52% | 91.5% |
| AtlasCloud | q8· fp8 | $0.2160 | $0.8800 | 2183ms / 4198ms | 17 / 32 tok/s | 99.78% | 99.8% |
| ModelRun | q4· fp4 | $0.2200 | $0.8000 | 1176ms / 3565ms | 28 / 46 tok/s | 99.92% | 98.4% |
| SiliconFlow | q8· fp8 | $0.2500 | $1.0000 | 1294ms / 3637ms | 15 / 26 tok/s | 99.18% | 98.5% |
| Novita | q8· fp8 | $0.2700 | $1.1200 | 1148ms / 2144ms | 23 / 33 tok/s | 99.95% | 99.8% |
| GMICloud | q8· fp8 | $0.2900 | $1.1400 | 3704ms / 5900ms | 10 / 27 tok/s | 90.67% | 93.2% |
“—” 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 0324
- 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 0324 that’s currently DeepInfra at $0.20/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.