Qwen3.6 Max Preview

qwen/qwen3.6-max-preview

Qwen (Alibaba)· 262K ctx

API onlytool callreasoningstructured quant: unknown

spread (output, p90 ÷ p10)

— too few providers

$7.80 – $7.80 · 1 providers · max÷min 1.0×

1 provider priced · 2 offerings · 2 omitted (stale)

Including routers & resellers

Cheapest / median / spread use providers that serve the model on their own capacity: first-party lab, hyperscaler, inference host.

Provider classes in the stats:

Blended $/M assumptionsInput : output: 1Cache-hit share of input%

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
OpenRoutertiered router / aggregator	$1.03	$6.16	—	$1.49no cache price published
Kilo Gateway router / aggregator	$1.03	$6.16	—	$1.49no cache price published
Pioneer unclassified	$1.04	$6.24	$0.21	$1.09
NanoGPT router / aggregator	$1.04	$6.24	$0.52	$1.18
AIHubMixtiered router / aggregator	$1.27	$7.61	$0.13	$1.25
Vercel AI Gateway router / aggregator	$1.30	$7.80	$0.13	$1.28
Alibabafirst-party first-party lab	$1.30	$7.80	$0.13	$1.28
LLM Gateway router / aggregator	$1.30	$7.80	$0.13	$1.15
Merge Gateway router / aggregator	$1.31	$7.88	—	$1.91no cache price published
EmpirioLabs AItiered unclassified	$1.31	$7.88	$1.31	$1.91
Ofox reseller	$2.15	$12.86	$0.20	$1.98

Stale offerings (not in the spread) · 2

Last priced more than 3 days before the latest snapshot — shown for reference, never mixed into cheapest, median or spread.

NanoGPT qwen3.6-max-previewpay per token
Charm Hyper qwen3.6-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) qwen3.6-max-previewsubscription plan

Connect

Provider (default: cheapest output among direct providers)

$7.80 /M · first-party lab

opencode.json

{
  "provider": {
    "alibaba": {
      "npm": "@ai-sdk/openai-compatible",
      "options": {
        "baseURL": "https://dashscope-intl.aliyuncs.com/compatible-mode/v1"
      },
      "models": {
        "qwen3.6-max-preview": {}
      }
    }
  }
}

Set DASHSCOPE_API_KEY in your environment. Generated — verify against the OpenCode docs.

Output $/M over time7-day preview

Median line, min–max band. Pre-2026-09 points are catalog-recorded dates from models.dev git history, not provider effective dates.

Data: models.dev (MIT), snapshot 2026-09-20. Prices are vendor-published; verify before purchase. Methodology.