Step 5 Preview
stepfun-ai/step-5-preview
spread (output, p90 ÷ p10)
— too few providers
$2.70 – $2.70 · 3 providers · max÷min 1.0×
Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.
blended = 90.9% input × [(1 − 70% cache) × input + 70% cache × cache-read] + 9.1% × output + cache writes (30% of uncached input) where a write price is published
A provider that publishes no cache price is blended with cache share 0 (all input at the input price) and labelled “no cache price published” — never penalised against identical in/out prices.
| Provider | Input | Output | Cache rd | Blended |
|---|---|---|---|---|
Deep Infra inference host | $1.00 | $2.70 | $0.10 | $0.58 |
Eden AI router / aggregator | $1.00 | $2.70 | $0.10 | $0.58 |
EmpirioLabs AI unclassified | $1.00 | $2.70 | $0.05 | $0.55 |
Kilo Gateway router / aggregator | $1.00 | $2.70 | $0.10 | $0.58 |
NanoGPT router / aggregator | $1.00 | $2.70 | $0.05 | $0.55 |
Novita AI inference host | $1.00 | $2.70 | $0.10 | $0.58 |
OpenCode Go subscription plan | $1.00 | $2.70 | $0.10 | $0.58 |
Vercel AI Gateway router / aggregator | $1.00 | $2.70 | $0.10 | $0.58 |
CommandCode unclassified | $1.00 | $2.70 | $0.05 | $0.55 |
OpenRouter router / aggregator | $1.00 | $2.70 | $0.10 | $0.58 |
Requesty router / aggregator | $1.00 | $2.70 | $0.05 | $0.55 |
StepFun (Global)first-party first-party lab | $1.00 | $2.70 | $0.05 | $0.55 |
AIHubMix router / aggregator | $1.08 | $3.09 | $0.05 | $0.61 |
AI/ML API unclassified | $1.38 | $3.71 | $0.07 | $0.76 |
Unpriced · 2
Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.
- OpenCode step-5-preview-freeunpriced
- OpenCode Go step-5-preview-freeunpriced
Data: models.dev (MIT), snapshot 2026-10-17. Prices are vendor-published; verify before purchase. Methodology.