#NVIDIA custom provider hangs with thinking=medium — no way to disable per provider

1 messages · Page 1 of 1 (latest)

graceful portal
#

Hey, I have a custom NVIDIA provider (integrate.api.nvidia.com) set as primary model. OpenClaw auto-sets thinking=medium but NVIDIA API doesn't support it — bot returns cached "Standing by" instead of responding. Is there a way to disable thinking for custom providers? Version 2026.5.6