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

GLM-4.5-Air

zhipuai· 2025-07-28· 131K ctx· mit
open weightstool callstructured quant: unknown

spread (output)

3.8×

$0.291 – $1.10 · 19 providers

19 providers priced
ProviderInputOutputCache rdBlended
ZenMuxtiered
relay router
$0.117$0.291$0.023$0.073
submodel
relay router
$0.100$0.500—$0.136*
NanoGPT
relay router
$0.120$0.800$0.060$0.144
NanoGPT
relay router
$0.120$0.800$0.060$0.144
Hugging Face
relay router
$0.130$0.850—$0.196*
Kilo Gateway
relay router
$0.130$0.850$0.025$0.129
DevPass (LLM Gateway)
relay router
$0.130$0.850$0.025$0.129
LLM Gateway
relay router
$0.130$0.850$0.025$0.129
NovitaAI
relay router
$0.130$0.850$0.025$0.129
OpenRouter
unknown
$0.130$0.850$0.025$0.129
SiliconFlow (China)
relay router
$0.140$0.860—$0.206*
SiliconFlow
relay router
$0.140$0.860—$0.206*
LLM Gateway
relay router
$0.200$1.10$0.030$0.174
Vercel AI Gateway
unknown
$0.200$1.10$0.030$0.174
Z.AI
relay router
$0.200$1.10$0.030$0.174
Merge Gateway
unknown
$0.200$1.10$0.030$0.174
Zhipu AI
first party lab
$0.200$1.10$0.030$0.174
Impossibl
relay router
$0.200$1.10$0.030$0.174
OrcaRouter
relay router
$0.200$1.10$0.030$0.174

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