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

qwen/qwen3.8-max

qwen· 1M ctx
API onlytool callreasoningstructured quant: unknown

spread (output)

1.6×

$4.80 – $7.50 · 27 providers

27 providers priced
ProviderInputOutputCache rdBlended
Alibaba Token Plan
relay router
free/—free/—$0free/—
Kenari
relay router
free/—free/——free/—
Alibaba Token Plan (China)
relay router
free/—free/—$0free/—
Alibaba Token Plan (China)
relay router
free/—free/—$0free/—
Alibaba Token Plan
relay router
free/—free/—$0free/—
SCNet Token Plan
relay router
free/—free/—$0free/—
Vancine
relay router
$1.60$4.80$0.200$1.00
Deep Infra
open weights host
$1.65$4.95$0.206$1.03
AIHubMix
unknown
$1.69$5.07$0.169$1.20
Ofox
relay router
$1.71$5.14$0.170$1.22
Alibaba (China)
relay router
$1.78$5.33$0.222$1.29
SCX.ai
relay router
$1.81$5.45$0.170$1.30
CrossModel
relay router
$1.88$5.63$0.230$1.36
Ofox
relay router
$2.00$6.00$0.250$1.45
OpenCode Go
relay router
$2.00$6.00$0.250$1.45
OrcaRouter
relay router
$2.00$6.00$0.250$1.45
Requesty
relay router
$2.00$6.00$0.250$1.45
Abacus
relay router
$2.00$6.00—$2.36*
Alibaba
first party lab
$2.00$6.00$0.250$1.45
ClinePass
relay router
$2.00$6.00$0.250$1.45
DigitalOcean
relay router
$2.00$6.00$0.200$1.22
Eden AI
relay router
$2.00$6.00$0.250$1.45
EmpirioLabs AI
relay router
$2.00$6.00$2.00$2.36
Charm Hyper
relay router
$2.00$6.00$0.250$1.25
DevPass (LLM Gateway)
relay router
$2.00$6.00$0.250$1.45
LLM Gateway
relay router
$2.00$6.00$0.250$1.25
LLM Gateway
relay router
$2.00$6.00$0.250$1.45
Merge Gateway
unknown
$2.00$6.00$0.250$1.25
NanoGPT
relay router
$2.00$6.00$0.250$1.45
302.AIoutlier
relay router
$2.16$6.36—$2.54*
above.devoutlier
relay router
$2.20$6.60$0.275$1.38
Impossibloutlier
relay router
$2.50$7.50—$2.95*
Venice AIoutlier
unknown
$2.50$7.50$0.313$1.82

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