Qwen3.7 Max

qwen/qwen3.7-max

Qwen (Alibaba)· 1M ctx

API onlytool callreasoning quant: unknown

spread (output, p90 ÷ p10)

2.0×

$3.75 – $8.05 · 6 providers · max÷min 2.1×

6 providers priced · 7 offerings · 1 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
Merge Gateway router / aggregator	$0.82	$2.48	$0.17	$0.56
OrcaRouter router / aggregator	$1.25	$3.75	$0.25	$0.97
Together AI inference host	$1.25	$3.75	$0.13	$0.76
Pioneer unclassified	$1.25	$3.75	$0.25	$0.97
NovitaAI inference host	$1.25	$3.75	$0.25	$0.97
Cloudflare AI Gateway router / aggregator	$1.25	$3.75	$0.25	$0.84
LLM Gateway router / aggregator	$1.25	$3.75	$0.25	$0.84
Kilo Gateway router / aggregator	$1.48	$4.42	$0.29	$1.14
OpenRouter router / aggregator	$1.48	$4.42	$0.29	$1.14
AIHubMix router / aggregator	$1.69	$5.07	$0.17	$1.20
Ofox reseller	$1.71	$5.14	$0.17	$1.22
302.AI reseller	$1.80	$5.30	—	$2.12no cache price published
CrossModel router / aggregator	$1.88	$5.63	$0.38	$1.46
Impossibl unclassified	$2.50	$7.50	$0.50	$1.68
GMI Cloud inference host	$2.50	$7.50	$0.25	$1.78
EmpirioLabs AI unclassified	$2.50	$7.50	$2.50	$2.95
Deep Infratiered inference host	$2.50	$7.50	$0.50	$1.68
ZenMux router / aggregator	$2.50	$7.50	$0.50	$1.94
Vercel AI Gateway router / aggregator	$2.50	$7.50	$0.50	$1.94
Charm Hyper unclassified	$2.50	$7.50	$0.50	$1.68
NanoGPT router / aggregator	$2.50	$7.50	$0.50	$1.94
OpenCode Go subscription plan	$2.50	$7.50	$0.50	$1.94
Alibaba (China)CNfirst-party first-party lab	$2.50	$7.50	$0.50	$1.94
Requesty router / aggregator	$2.50	$7.50	$0.25	$1.78
Abacus router / aggregator	$2.50	$7.50	—	$2.95no cache price published
Venice AI inference host	$2.70	$8.05	$0.27	$1.91
Modelis reseller	$3.00	$9.00	—	$3.55no 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 qwen3.7-maxpay per token

Subscription plans (flat fee, not per-token) · 6

Flat-fee plan — the per-token price is bundled into a subscription, so $0/token is not free. Excluded from cheapest, median and spread.

Alibaba Token Plan (China) qwen3.7-maxMainland-China endpointsubscription plan
Alibaba Token Plan qwen3.7-maxsubscription plan
DevPass (LLM Gateway) qwen3.7-maxsubscription plan
ClinePass cline-pass/qwen3.7-maxsubscription plan
Alibaba Coding Plan (China) qwen3.7-maxMainland-China endpointsubscription plan
Alibaba Coding Plan qwen3.7-maxsubscription plan

Connect

Provider (default: cheapest output among direct providers)

$3.75 /M · inference host

opencode.json

{
  "provider": {
    "togetherai": {
      "npm": "@ai-sdk/togetherai",
      "models": {
        "Qwen/Qwen3.7-Max": {}
      }
    }
  }
}

Set TOGETHER_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.