Qwen3.5 Flash
qwen/qwen3.5-flash
spread (output, p90 ÷ p10)
— too few providers
$1.03 – $1.03 · 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 |
|---|---|---|---|---|
OpenRouter router / aggregator | $0.0650 | $0.260 | — | $0.0827no cache price published |
Merge Gateway router / aggregator | $0.0290 | $0.287 | $0.00580 | $0.0377 |
EmpirioLabs AI unclassified | $0.0900 | $0.368 | $0.0900 | $0.115 |
Ofox reseller | $0.100 | $0.400 | $0.0100 | $0.0802 |
OrcaRouter router / aggregator | $0.100 | $0.400 | — | $0.127no cache price published |
Vercel AI Gateway router / aggregator | $0.100 | $0.400 | $0.0100 | $0.0802 |
ZenMux router / aggregator | $0.100 | $0.400 | — | $0.127no cache price published |
NanoGPT router / aggregator | $0.100 | $0.400 | $0.0500 | $0.0955 |
Alibaba (China)CNfirst-partytiered first-party lab | $0.17 | $1.03 | — | $0.25no cache price published |
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.
- NanoGPT qwen3.5-flashpay per token
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.