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

GLM-4.5

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

spread (output)

2.8×

$0.800 – $2.20 · 20 providers

20 providers priced
ProviderInputOutputCache rdBlended
ModelScope
relay router
free/—free/——free/—
submodelfp8
relay router
$0.200$0.800—$0.255*
302.AI
relay router
$0.286$1.14—$0.364*
ZenMuxtiered
relay router
$0.291$1.16$0.058$0.222
NanoGPT
relay router
$0.300$1.30$0.150$0.296
NanoGPT
relay router
$0.300$1.30$0.150$0.296
DevPass (LLM Gateway)
relay router
$0.600$2.20$0.110$0.434
LLM Gateway
relay router
$0.600$2.20$0.110$0.434
LLM Gateway
relay router
$0.600$2.20$0.110$0.434
Merge Gateway
unknown
$0.600$2.20$0.110$0.434
Hugging Face
relay router
$0.600$2.20—$0.746*
NovitaAI
relay router
$0.600$2.20$0.110$0.434
OpenRouter
unknown
$0.600$2.20$0.110$0.434
OrcaRouter
relay router
$0.600$2.20$0.110$0.434
Abacus
relay router
$0.600$2.20—$0.746*
Vercel AI Gateway
unknown
$0.600$2.20$0.110$0.434
Z.AI
relay router
$0.600$2.20$0.110$0.434
Impossibl
relay router
$0.600$2.20$0.110$0.434
Zhipu AI
first party lab
$0.600$2.20$0.110$0.434
Jiekou.AI
relay router
$0.600$2.20—$0.746*
Kilo Gateway
relay router
$0.600$2.20$0.110$0.434

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