Loading
Z.ai
z-ai/glm-5.3-prime
Published by the vendor; the platform bills at the target's declared price.
Z.ai z-ai/glm-5.3-prime
GLM-5.3-Prime is the high-speed variant of Z.ai's GLM-5.3, inheriting its full capabilities while delivering 1.5–2× the output throughput through inference acceleration. It supports text input and output with a 1M-token...
Cached input reads $0.56 per 1M
Nothing on this deployment answers as this model yet. Connect your own provider under Model providers, or add a target to your catalogue - the router picks it up without retraining.
# targets.yaml - declare a target that runs GLM 5.3 Prime
targets:
- id: glm-5-3-prime
kind: llm
name: GLM 5.3 Prime
metadata:
model: z-ai/glm-5.3-prime # links the target to this catalogue entry
capabilities:
domains: [general]
supports_tools: true
context_window: 1000000
cost:
usd_per_1k_tokens: 0.005800Input list price per million tokens; GLM 5.3 Prime is the most expensive of 13 listed.
Other models by the same vendor in the catalogue.