inferenstack — the market read on AI inference · last observation 2026-09-20. See the boards
Price spread

Qwen3.5 Plus

alibaba· 2026-02-16· 1M ctx
API onlytool callreasoning quant: unknown

spread (output)

7.0×

$0.688 – $4.80 · 15 providers

15 providers priced
ProviderInputOutputCache rdBlended
Alibaba Coding Plan (China)
relay router
free/—free/—$0free/—
Alibaba Coding Plan
relay router
free/—free/—$0free/—
OrcaRouter
relay router
$0.115$0.688—$0.167*
Merge Gateway
unknown
$0.115$0.688$0.023$0.109
302.AI
relay router
$0.120$0.690—$0.172*
OpenCode Zen
relay router
$0.200$1.20$0.020$0.197
OpenCode Go
relay router
$0.200$1.20$0.020$0.197
Alibaba (China)tiered
relay router
$0.287$1.72—$0.418*
EmpirioLabs AItiered
relay router
$0.360$2.21$0.360$0.528
Ofox
relay router
$0.400$2.40$0.040$0.386
Alibaba
first party lab
$0.400$2.40—$0.582*
Ofox
relay router
$0.400$2.40$0.040$0.386
LLMTR
relay router
$0.400$2.40—$0.582*
Meganova
relay router
$0.400$2.40—$0.582*
NanoGPT
relay router
$0.400$2.40$0.040$0.353
Vercel AI Gateway
unknown
$0.400$2.50$0.040$0.403
ZenMuxoutlier
relay router
$0.800$4.80—$1.16*

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