Qwen3.8 Max Preview

qwen/qwen3.8-max-preview

Qwen (Alibaba)· 1M ctx

API onlytool callreasoning quant: unknown

spread (output, p90 ÷ p10)

1.1×

$4.95 – $7.50 · 6 providers · max÷min 1.5×

6 providers priced · 7 offerings

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
AIHubMix router / aggregator	$0.34	$1.01	$0.07	$0.26
LLM Gateway router / aggregator	$1.54	$4.63	$0.20	$1.17
Vancine reseller	$1.60	$4.80	$0.20	$1.00
Deep Infra inference host	$1.65	$4.95	$0.21	$1.03
Ofox reseller	$1.71	$5.14	$0.17	$1.22
Alibaba (China)CNfirst-party first-party lab	$1.78	$5.33	$0.22	$1.29
SCX.ai unclassified	$1.81	$5.45	$0.17	$1.30
CrossModel router / aggregator	$1.88	$5.63	$0.23	$1.36
OpenCode Go subscription plan	$2.00	$6.00	$0.25	$1.45
Opper router / aggregator	$2.00	$6.00	$0.25	$1.25
Requesty router / aggregator	$2.00	$6.00	$0.25	$1.45
OrcaRouter router / aggregator	$2.00	$6.00	$0.25	$1.45
Abacus router / aggregator	$2.00	$6.00	$0.25	$1.25
CommandCode unclassified	$2.00	$6.00	$0.25	$1.45
DigitalOcean inference host	$2.00	$6.00	$0.20	$1.22
Eden AI router / aggregator	$2.00	$6.00	$0.25	$1.45
EmpirioLabs AI unclassified	$2.00	$6.00	$2.00	$2.36
GMI Cloud inference host	$2.00	$6.00	$0.25	$1.45
Charm Hyper unclassified	$2.00	$6.00	$0.25	$1.25
Merge Gateway router / aggregator	$2.00	$6.00	$0.25	$1.45
NanoGPT router / aggregator	$2.00	$6.00	$0.25	$1.45
Novita AI inference host	$2.00	$6.00	$0.25	$1.25
OpenCode router / aggregator	$2.00	$6.00	$0.25	$1.45
302.AI reseller	$2.16	$6.36	$0.17	$1.49
above.dev unclassified	$2.20	$6.60	$0.28	$1.38
Kenari unclassified	$2.40	$6.86	$0.30	$1.71
Impossibl unclassified	$2.50	$7.50	—	$2.95no cache price published
Venice AIoutlier inference host	$2.50	$7.50	$0.31	$1.82

Subscription plans (flat fee, not per-token) · 7

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) qwen3.8-max-previewMainland-China endpointsubscription plan
Alibaba Token Plan qwen3.8-max-previewsubscription plan
SCNet Token Plan Qwen3.8-MaxMainland-China endpointsubscription plan
Alibaba Token Plan qwen3.8-maxsubscription plan
Alibaba Token Plan (China) qwen3.8-maxMainland-China endpointsubscription plan
DevPass (LLM Gateway) qwen3.8-maxsubscription plan
ClinePass cline-pass/qwen3.8-maxsubscription plan

Unpriced · 1

Listed at $0 with no published pricing — we can't tell whether it's free, bundled or just missing. Excluded from cheapest, median and spread.

AIHubMix qwen3.8-max-freeunpriced

Connect

Provider (default: cheapest output among direct providers)

$4.95 /M · inference host

opencode.json

{
  "provider": {
    "deepinfra": {
      "npm": "@ai-sdk/deepinfra",
      "models": {
        "Qwen/Qwen3.8-Max": {}
      }
    }
  }
}

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

Not enough history yet — the min/median/max sparkline fills in as the daily snapshot accumulates.

Data: models.dev (MIT), snapshot 2026-10-27. Prices are vendor-published; verify before purchase. Methodology.