Qwen Max
qwen/qwen-max
spread (output, p90 ÷ p10)
— too few providers
$1.38 – $6.00 · 2 providers · max÷min 4.4×
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 |
|---|---|---|---|---|
Alibaba (China)CNfirst-party first-party lab | $0.34 | $1.38 | — | $0.44no cache price published |
Ofox reseller | $0.35 | $1.38 | $0.07 | $0.26 |
Fireworks AI inference host | $2.00 | $6.00 | $0.25 | $1.25 |
NanoGPT router / aggregator | $1.60 | $6.39 | $0.80 | $1.53 |
LLM Gateway router / aggregator | $1.60 | $6.40 | — | $2.04no cache price published |
Eden AI router / aggregator | $1.60 | $6.40 | $0.32 | $1.22 |
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 qwen-maxpay per token
Subscription plans (flat fee, not per-token) · 1
Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.
- DevPass (LLM Gateway) qwen-maxsubscription plan
Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.