diff --git a/docs/concepts/model-failover.md b/docs/concepts/model-failover.md
index 18cbcb5120b..3ce2cf1cc18 100644
--- a/docs/concepts/model-failover.md
+++ b/docs/concepts/model-failover.md
@@ -155,12 +155,15 @@ State is stored in `auth-profiles.json` under `usageStats`:
 
 Billing/credit failures (for example “insufficient credits” / “credit balance too low”) are treated as failover‑worthy, but they’re usually not transient. Instead of a short cooldown, OpenClaw marks the profile as **disabled** (with a longer backoff) and rotates to the next profile/provider.
 
-Not every HTTP `402` lands here. OpenClaw classifies temporary `402` usage-window
-and organization/workspace spend-limit errors as `rate_limit` when the message
-looks retryable (for example `weekly usage limit exhausted`, `daily limit
-reached, resets tomorrow`, or `organization spending limit exceeded`). Those
-stay on the short cooldown/failover path instead of the long billing-disable
-path.
+Not every billing-shaped response is `402`, and not every HTTP `402` lands
+here. OpenClaw keeps explicit billing text in the billing lane even when a
+provider returns `401` or `403` instead (for example OpenRouter `403 Key limit
+exceeded`). Meanwhile temporary `402` usage-window and
+organization/workspace spend-limit errors are classified as `rate_limit` when
+the message looks retryable (for example `weekly usage limit exhausted`, `daily
+limit reached, resets tomorrow`, or `organization spending limit exceeded`).
+Those stay on the short cooldown/failover path instead of the long
+billing-disable path.
 
 State is stored in `auth-profiles.json`:
 
diff --git a/docs/gateway/configuration-reference.md b/docs/gateway/configuration-reference.md
index 6a374a7426a..46f472750b4 100644
--- a/docs/gateway/configuration-reference.md
+++ b/docs/gateway/configuration-reference.md
@@ -3130,9 +3130,11 @@ Notes:
 ```
 
 - `billingBackoffHours`: base backoff in hours when a profile fails due to true
-  billing/insufficient-credit errors (default: `5`). Retryable HTTP `402`
-  usage-window or organization/workspace spend-limit messages stay in the
-  `rate_limit` path instead.
+  billing/insufficient-credit errors (default: `5`). Explicit billing text can
+  still land here even on `401`/`403` responses (for example OpenRouter
+  `Key limit exceeded`). Retryable HTTP `402` usage-window or
+  organization/workspace spend-limit messages stay in the `rate_limit` path
+  instead.
 - `billingBackoffHoursByProvider`: optional per-provider overrides for billing backoff hours.
 - `billingMaxHours`: cap in hours for billing backoff exponential growth (default: `24`).
 - `authPermanentBackoffMinutes`: base backoff in minutes for high-confidence `auth_permanent` failures (default: `10`).
diff --git a/docs/help/faq.md b/docs/help/faq.md
index f21b5fa83d8..cbbba0d62d2 100644
--- a/docs/help/faq.md
+++ b/docs/help/faq.md
@@ -2419,10 +2419,14 @@ for usage/billing and raise limits as needed.
     `ThrottlingException`, `resource exhausted`, and periodic usage-window
     limits (`weekly/monthly limit reached`) as failover-worthy rate limits.
 
-    Some HTTP `402` responses also stay in that transient bucket. If the
-    message looks like a retryable usage-window or organization/workspace spend
-    limit (`daily limit reached, resets tomorrow`, `organization spending limit
-    exceeded`), OpenClaw treats it as `rate_limit`, not a long billing disable.
+    Some billing-looking responses are not `402`, and some HTTP `402`
+    responses also stay in that transient bucket. If a provider returns
+    explicit billing text on `401` or `403` (for example OpenRouter
+    `Key limit exceeded`), OpenClaw keeps that in the billing lane. If a `402`
+    message instead looks like a retryable usage-window or
+    organization/workspace spend limit (`daily limit reached, resets tomorrow`,
+    `organization spending limit exceeded`), OpenClaw treats it as
+    `rate_limit`, not a long billing disable.
 
     Context-overflow errors are different: signatures such as
     `request_too_large`, `input exceeds the maximum number of tokens`, or