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

alibaba/qwen3-max-thinking

alibaba· 256K ctx
open weightstool callreasoning quant: unknown

spread (output)

1.5×

$3.90 – $6.00 · 3 providers

3 providers priced
ProviderInputOutputCache rdBlended
Kilo Gateway
relay router
$0.780$3.90—$1.06*
OpenRoutertiered
unknown
$0.780$3.90—$1.06*
Vercel AI Gateway
unknown
$1.20$6.00$0.240$1.03

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