InferPrice

All models

GLM-5.3 API pricing

GLM-5.3 by Z.ai is cheapest at Together AI and Fireworks and Baseten: $1.40 input and $4.40 output per 1M tokens. Compared across 3 providers.

ProviderInput $/1MOutput $/1MBlended 3:1Notes
Together AI$1.40$4.40$2.15source
Fireworks$1.40$4.40$2.15Standard tiersource
Baseten$1.40$4.40$2.15source

Providers may serve different quantizations or speed tiers of the same model, so check the notes. Last checked 2026-10-12.