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

Qwen3 Max

alibaba· 2025-09-23· 256K ctx
API onlytool callreasoning quant: unknown

spread (output)

5.9×

$1.43 – $8.45 · 23 providers

23 providers priced
ProviderInputOutputCache rdBlended
Alibaba Coding Plan
relay router
free/—free/—$0free/—
Alibaba Coding Plan (China)
relay router
free/—free/—$0free/—
iFlow
relay router
free/—free/——free/—
iFlow
relay router
free/—free/——free/—
Ofox
relay router
$0.360$1.43$0.072$0.274
Ofox
relay router
$0.360$1.43$0.072$0.274
Merge Gateway
unknown
$0.359$1.43$0.072$0.274
OrcaRouter
relay router
$0.359$1.43—$0.457*
DevPass (LLM Gateway)
relay router
$0.845$3.38$0.600$1.23
LLM Gateway
relay router
$0.845$3.38—$1.08*
OpenRoutertiered
unknown
$0.780$3.90$0.156$0.747
Kilo Gateway
relay router
$0.780$3.90$0.156$0.747
EmpirioLabs AItiered
relay router
$1.08$5.52$1.08$1.48
ZenMux
relay router
$1.20$6.00—$1.64*
Alibaba
first party lab
$1.20$6.00—$1.64*
Cloudflare AI Gateway
unknown
$1.20$6.00—$1.64*
Deep Infratiered
open weights host
$1.20$6.00$0.240$1.03
Eden AI
relay router
$1.20$6.00$0.240$1.15
Eden AI
relay router
$1.20$6.00$0.240$1.15
LLM Gateway
relay router
$1.20$6.00$0.240$1.15
LLMTR
relay router
$1.20$6.00—$1.64*
Vercel AI Gateway
unknown
$1.20$6.00$0.240$1.03
Vercel AI Gateway
unknown
$1.20$6.00$0.240$1.03
Abacus
relay router
$1.20$6.00—$1.64*
NanoGPT
relay router
$1.20$6.00$0.600$1.26
Alibaba (China)tiered
relay router
$1.29$7.75—$1.88*
NovitaAI
relay router
$2.11$8.45—$2.69*

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