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

Qwen3.7 Flash

alibaba· 2026-07-15· 1M ctx
API onlytool callreasoning quant: unknown

spread (output)

7.1×

$0.113 – $0.800 · 12 providers

12 providers priced · 1 omitted (stale)
ProviderInputOutputCache rdBlended
AIHubMix
unknown
$0.028$0.113$0.0056$0.024
Alibaba (China)tiered
relay router
$0.030$0.118$0.0030$0.024
EmpirioLabs AItiered
relay router
$0.030$0.130$0.0060$0.024
Kilo Gateway
relay router
$0.030$0.130$0.0060$0.027
DevPass (LLM Gateway)
relay router
$0.030$0.130$0.0060$0.027
LLM Gateway
relay router
$0.030$0.130$0.0060$0.027
NanoGPTstale
relay router
$0.030$0.130$0.0060$0.027
NanoGPT
relay router
$0.030$0.130$0.0060$0.027
OpenRoutertiered
unknown
$0.030$0.130$0.0060$0.027
OrcaRouter
relay router
$0.030$0.130$0.0060$0.027
Vercel AI Gateway
unknown
$0.030$0.130$0.0060$0.027
CrossModeltiered
relay router
$0.040$0.130$0.010$0.032
Charm Hyperoutlier
relay router
$0.200$0.800$0.040$0.153

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