Qwen3.8 Flash Next
qwen/qwen3.8-flash-next
spread (output, p90 ÷ p10)
— too few providers
$0.470 – $0.470 · 1 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 |
|---|---|---|---|---|
AMD inference host | $0.150 | $0.470 | $0.0160 | $0.0938 |
Requesty router / aggregator | $0.200 | $0.500 | $0.0500 | $0.132 |
TensorX unclassified | $0.200 | $0.500 | $0.0500 | $0.132 |
Cortecs router / aggregator | $0.201 | $0.500 | $0.0500 | $0.132 |
Stale offerings (not in the spread) · 1
Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.
- Vercel AI Gateway alibaba/qwen3.8-flash-nextpay per token
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.