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

Qwen3.8 Flash

alibaba· 2026-08-26· 992K ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

1.5×

$0.380 – $0.564 · 23 providers

23 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
NaN
relay router
free/—free/——free/—
Alibaba Token Plan
relay router
free/—free/—$0free/—
Alibaba Token Plan (China)
relay router
free/—free/—$0free/—
SCNet Token Plan
relay router
free/—free/—$0free/—
Vancine
relay router
$0.120$0.380$0.013$0.076
AIHubMix
unknown
$0.113$0.380$0.014$0.089
Deep Infra
open weights host
$0.113$0.382$0.014$0.075
Ofox
relay router
$0.110$0.390$0.011$0.084
Alibaba (China)
relay router
$0.119$0.401$0.012$0.089
NanoGPT
relay router
$0.140$0.420$0.016$0.103
CrossModel
relay router
$0.130$0.430$0.016$0.101
OpenCode Zen
relay router
$0.150$0.470$0.016$0.110
OpenCode Go
relay router
$0.150$0.470$0.016$0.110
OpenRouter
unknown
$0.150$0.470$0.016$0.110
Requesty
relay router
$0.160$0.470$0.016$0.113
Vercel AI Gateway
unknown
$0.150$0.470$0.016$0.110
Alibaba
first party lab
$0.150$0.470$0.016$0.110
Eden AI
relay router
$0.150$0.470$0.016$0.110
EmpirioLabs AI
relay router
$0.160$0.470$0.160$0.188
Charm Hyper
relay router
$0.150$0.470$0.016$0.094
Kilo Gateway
relay router
$0.150$0.470$0.016$0.110
DevPass (LLM Gateway)
relay router
$0.150$0.470$0.016$0.110
LLM Gateway
relay router
$0.150$0.470$0.016$0.110
LLM Gateway
relay router
$0.150$0.470$0.016$0.094
NanoGPTstale
relay router
$0.160$0.470$0.016$0.113
Ofox
relay router
$0.150$0.470$0.016$0.110
Venice AI
unknown
$0.140$0.490$0.014$0.092
302.AIoutlier
relay router
$0.180$0.564—$0.215*

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