Skip to main content
Gclaw uses the Kimi-K2.5 model for inference, running on Gcore H200 GPUs.

​
Model limits

LimitValue
Context window200,000 tokens
Maximum output32,000 tokens
ReasoningEnabled

​
Rate limits

Rate limits are managed at the Gcore infrastructure level and depend on the account tier. If rate limiting errors occur, reduce request frequency or contact Gcore support.

​
Instance limits

During the beta period, each account is limited to one Gclaw instance.