We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
1 parent b0297a3 commit d73a2b1Copy full SHA for d73a2b1
docs/tiers.md
@@ -419,6 +419,10 @@ spec:
419
- expression: auth.identity.userid
420
```
421
422
+> [!NOTE]
423
+> This policy is applied to the `HTTPRoute` resource that handles the model inference requests, so it is specific to the particular model.
424
+> It can also be applied to the `Gateway` resource, and so it would apply to all models attached to this gateway.
425
+
426
**Token-based limits** track LLM token consumption. Configure similarly with token counters.
427
428
**Apply:**
0 commit comments