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

z-ai/glm-latest

z-ai· 1.0M ctx
open weightstool callreasoningstructured quant: unknown

spread (output)

3.4×

$2.65 – $8.94 · 5 providers

5 providers priced
ProviderInputOutputCache rdBlended
Kilo Gateway
relay router
$0.844$2.65$0.157$0.571
OpenRouter
unknown
$0.844$2.65$0.157$0.571
NanoGPT
relay router
$1.00$3.20$0.200$0.691
Fireworks AI
relay router
$1.40$4.40$0.260$0.948
Privatemode AIoutlier
relay router
$1.79$8.94$0.173$1.41

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