StepFun: Step 3.5 Flash
stepfun/step-3.5-flash
Cheapest provider
$0.09 / 1M
DeepInfra
Fastest provider (p95)
201 tok/s
StepFun
Intelligence (estimated)
52.7
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 | q8· fp8 | $0.0900 | $0.3000 | 410ms / 1679ms | 40 / 54 tok/s | 97.23% | 99.2% |
| SiliconFlow | q8· fp8 | $0.1000 | $0.3000 | 3314ms / 6433ms | 44 / 73 tok/s | 100.00% | 100.0% |
| StepFun | q8· fp8 | $0.1000 | $0.3000 | 887ms / 2159ms | 135 / 201 tok/s | 100.00% | 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.
- ·unknown family base
- ·v3.5 generation +3
- ·top-19 on OpenRouter +0
Want a curated score? File a benchmark report and we’ll add it to the next sync.
How Atlas routes StepFun: Step 3.5 Flash
- 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 StepFun: Step 3.5 Flash that’s currently DeepInfra at $0.09/1M.
- Batch tier — async, biggest discount. Roadmapped to use provider batch APIs (OpenAI / Anthropic) where available and queued spot capacity for open-weight workloads.