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

Qwen Plus

alibaba· 2024-01-25· 131K ctx
API onlytool call quant: unknown

spread (output)

4.2×

$0.287 – $1.20 · 13 providers

13 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
Alibaba (China)
relay router
$0.115$0.287$0.012$0.077
Merge Gateway
unknown
$0.115$0.287$0.023$0.072
Ofox
relay router
$0.120$0.290$0.023$0.074
Ofox
relay router
$0.120$0.290$0.023$0.074
Kilo Gateway
relay router
$0.260$0.780$0.052$0.202
OpenRoutertiered
unknown
$0.260$0.780$0.052$0.202
LLMTR
relay router
$0.400$1.20—$0.473*
DevPass (LLM Gateway)
relay router
$0.400$1.20$0.080$0.310
DevPass (LLM Gateway)
relay router
$0.400$1.20$0.080$0.310
LLM Gateway
relay router
$0.400$1.20$0.080$0.310
LLM Gateway
relay router
$0.400$1.20$0.080$0.310
Alibaba
first party lab
$0.400$1.20—$0.473*
NanoGPT
relay router
$0.400$1.20$0.200$0.345
NanoGPTstale
relay router
$0.400$1.20$0.200$0.345

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