Limits and quotas

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

Model limits

Limit	Value
Context window	200,000 tokens
Maximum output	32,000 tokens
Reasoning	Enabled

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.