Model trigger
Names the model that makes this workflow run. Exactly one per workflow.
The match is exact. A request for any other model leaves the workflow alone.
Model selection
Terminal node. Names the model the request will actually run on.
The first branch that reaches one of these wins, and the walk stops there.
Metric check
The most useful node, and the only one that branches. It aggregates your own recorded usage for a model over a window and compares it against a threshold.
Each condition is a metric, an operator and a threshold over a time window.
Operators are less than, less or equal, equal, greater or equal, greater than.
Windows are 1 hour, 6 hours, 24 hours, 7 days or 30 days.
The node emits success when every condition passes and failure
otherwise, and you wire a different edge to each.
Wire both outputs. An edge leaving this node with no output assigned is never
followed.
Quota check
Reads one of your quota rules and branches on whether it is exhausted.
The meaning inverts with that setting. With fail, the node continues only
while the quota still has room. With continue, it continues only once the
quota is exhausted, which is how you build the fallback branch.
Quota rule event
Continues based on whether a named quota rule has reached its limit, using the usage already gathered for this request.Image detection
Continues based on whether the request carries an image.
Detection recognises OpenAI style
image_url content parts. Anthropic style
image blocks are not detected, so use this on the OpenAI endpoints.
Time and date conditions
Continues based on when the request arrived.
Times are evaluated in the gateway’s own timezone, which is UTC. There is no
timezone setting.
Condition
Combines the results of several upstream nodes into one decision.
It does not re-evaluate anything. It reads what the named nodes already
decided, which is what lets you express “if two of these three are true”.