Update HTTP error codes for Inference

inference/api-reference/errors.mdx

@@ -8,9 +8,9 @@ The following table lists common API errors you might encounter:
 | Error Code | Message | Cause | Solution |
 | ---------- | ------- | ----- | -------- |
 | 401 | Authentication failed | Your authentication credentials are incorrect or your W&B project entity and/or name are incorrect. | Ensure you're using the correct API key and that your W&B project name and entity are correct. |
+| 402 | You exceeded your current quota, please check your plan and billing details | Out of credits or reached monthly spending cap. | Get more credits or increase your limits. For more information, see [Usage information and limits](/inference/usage-limits/). |
 | 403 | Country, region, or territory not supported | Accessing the API from an unsupported location. | Please see [Geographic restrictions](/inference/usage-limits/#geographic-restrictions) |
+| 403 | W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference | The user is on a personal account, which doesn't have access to W&B Inference. | Switch to a non-personal account. If one isn't available, create a Team to create a non-personal account. For more information, see [Personal entities unsupported](/inference/usage-limits/#personal-entities-unsupported). |
 | 429 | Concurrency limit reached for requests | Too many concurrent requests. | Reduce the number of concurrent requests or increase your limits. For more information, see [Usage information and limits](/inference/usage-limits/). |
-| 429 | You exceeded your current quota, please check your plan and billing details | Out of credits or reached monthly spending cap. | Get more credits or increase your limits. For more information, see [Usage information and limits](/inference/usage-limits/). |
-| 429 | W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference | The user is on a personal account, which doesn't have access to W&B Inference. | Switch to a non-personal account. If one isn't available, create a Team to create a non-personal account. For more information, see [Personal entities unsupported](/inference/usage-limits/#personal-entities-unsupported). |
 | 500 | The server had an error while processing your request | Internal server error. | Retry after a brief wait and contact support if it persists. |
 | 503 | The engine is currently overloaded, please try again later | Server is experiencing high traffic. | Retry your request after a short delay. |

models/support.mdx

@@ -1151,13 +1151,12 @@ def handle_inference_error(error):
     if "401" in error_str:
         # Invalid authentication
         raise ValueError("Check your API key and project configuration")
+    elif "402" in error_str:
+        # Out of credits
+        raise ValueError("Insufficient credits")
     elif "429" in error_str:
-        if "quota" in error_str:
-            # Out of credits
-            raise ValueError("Insufficient credits")
-        else:
-            # Rate limited
-            return "retry"
+        # Rate limited
+        return "retry"
     elif "500" in error_str or "503" in error_str:
         # Server error
         return "retry"
@@ -1188,6 +1187,22 @@ client = openai.OpenAI(
 </Accordion>
 </Update>
 
+<Update tags={["Inference"]}>
+<Accordion title="Why am I getting insufficient quota errors (402) with W&B Inference?">
+
+Insufficient quota errors (402) occur when you do not have remaining credits in your plan.
+
+**Error:** "You exceeded your current quota, please check your plan and billing details"
+
+**Solution:**
+
+- Check your credit balance in the W&B Billing page
+- Purchase more credits or upgrade your plan
+- Request a limit increase from [support](https://wandb.ai/site/contact)
+
+</Accordion>
+</Update>
+
 <Update tags={["Inference"]}>
 <Accordion title="Why does W&B Inference say my country or region is not supported?">
 
@@ -1229,7 +1244,7 @@ This is determined by your IP address location at the time of the API request.
 <Update tags={["Inference"]}>
 <Accordion title="Why isn't W&B Inference available for my personal account?">
 
-Personal accounts don't support W&B Inference. You'll see this 429 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
+Personal accounts don't support W&B Inference. You'll see this 403 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
 
 ## Background
 
@@ -1275,11 +1290,8 @@ If you're having trouble creating a team or switching from a personal account, c
 <Update tags={["Inference"]}>
 <Accordion title="Why am I getting rate limit errors (429) with W&B Inference?">
 
-Rate limit errors (429) occur when you exceed concurrency limits or run out of credits.
-
-## Types of 429 errors
+Rate limit errors (429) occur when you exceed concurrency limits.
 
-### Concurrency limit reached
 **Error:** "Concurrency limit reached for requests"
 
 **Solution:**
@@ -1288,22 +1300,6 @@ Rate limit errors (429) occur when you exceed concurrency limits or run out of c
 - Implement exponential backoff
 - Note: Rate limits apply per W&B project
 
-### Quota exceeded
-**Error:** "You exceeded your current quota, please check your plan and billing details"
-
-**Solution:**
-- Check your credit balance in the W&B Billing page
-- Purchase more credits or upgrade your plan
-- Request a limit increase from support
-
-### Personal account limitation
-**Error:** "W&B Inference isn't available for personal accounts"
-
-**Solution:**
-- Switch to a non-personal account
-- Create a Team to access W&B Inference
-- Personal entities were deprecated in May 2024
-
 ## Best practices to avoid rate limits
 
 1. **Implement retry logic with exponential backoff:**

models/support/inference_error_handling_best_practices.mdx

@@ -68,13 +68,12 @@ def handle_inference_error(error):
     if "401" in error_str:
         # Invalid authentication
         raise ValueError("Check your API key and project configuration")
+    elif "402" in error_str:
+        # Out of credits
+        raise ValueError("Insufficient credits")
     elif "429" in error_str:
-        if "quota" in error_str:
-            # Out of credits
-            raise ValueError("Insufficient credits")
-        else:
-            # Rate limited
-            return "retry"
+        # Rate limited
+        return "retry"
     elif "500" in error_str or "503" in error_str:
         # Server error
         return "retry"

models/support/inference_insufficient_quota_402_error.mdx

@@ -0,0 +1,13 @@
+---
+title: Why am I getting insufficient quota errors (402) with W&B Inference?
+---
+
+Insufficient quota errors (402) occur when you do not have remaining credits in your plan.
+
+**Error:** "You exceeded your current quota, please check your plan and billing details"
+
+**Solution:**
+
+- Check your credit balance in the W&B Billing page
+- Purchase more credits or upgrade your plan
+- Request a limit increase from [support](https://wandb.ai/site/contact)

models/support/inference_personal_account_limitation.mdx

@@ -2,7 +2,7 @@
 title: Why isn't W&B Inference available for my personal account?
 ---
 
-Personal accounts don't support W&B Inference. You'll see this 429 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
+Personal accounts don't support W&B Inference. You'll see this 403 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
 
 ## Background
 

models/support/inference_rate_limit_429_error.mdx

@@ -2,11 +2,8 @@
 title: Why am I getting rate limit errors (429) with W&B Inference?
 ---
 
-Rate limit errors (429) occur when you exceed concurrency limits or run out of credits.
+Rate limit errors (429) occur when you exceed concurrency limits.
 
-## Types of 429 errors
-
-### Concurrency limit reached
 **Error:** "Concurrency limit reached for requests"
 
 **Solution:**
@@ -15,22 +12,6 @@ Rate limit errors (429) occur when you exceed concurrency limits or run out of c
 - Implement exponential backoff
 - Note: Rate limits apply per W&B project
 
-### Quota exceeded
-**Error:** "You exceeded your current quota, please check your plan and billing details"
-
-**Solution:**
-- Check your credit balance in the W&B Billing page
-- Purchase more credits or upgrade your plan
-- Request a limit increase from support
-
-### Personal account limitation
-**Error:** "W&B Inference isn't available for personal accounts"
-
-**Solution:**
-- Switch to a non-personal account
-- Create a Team to access W&B Inference
-- Personal entities were deprecated in May 2024
-
 ## Best practices to avoid rate limits
 
 1. **Implement retry logic with exponential backoff:**

snippets/en/kb_article_map.mdx

@@ -577,6 +577,13 @@ export const kbArticleMap = [
     ],
     "title": "What are the best practices for handling W&B Inference errors?"
   },
+  {
+    "page": "/models/support/inference_insufficient_quota_402_error",
+    "tags": [
+      "inference"
+    ],
+    "title": "Why am I getting insufficient quota errors (402) with W&B Inference?"
+  },
   {
     "page": "/models/support/inference_geographic_restriction_403",
     "tags": [

support-tags.mdx

@@ -1123,13 +1123,12 @@ def handle_inference_error(error):
     if "401" in error_str:
         # Invalid authentication
         raise ValueError("Check your API key and project configuration")
+    elif "402" in error_str:
+        # Out of credits
+        raise ValueError("Insufficient credits")
     elif "429" in error_str:
-        if "quota" in error_str:
-            # Out of credits
-            raise ValueError("Insufficient credits")
-        else:
-            # Rate limited
-            return "retry"
+        # Rate limited
+        return "retry"
     elif "500" in error_str or "503" in error_str:
         # Server error
         return "retry"
@@ -1160,6 +1159,23 @@ client = openai.OpenAI(
 </Accordion>
 </Update>
 
+
+<Update tags={["Inference"]}>
+<Accordion title="Why am I getting insufficient quota errors (402) with W&B Inference?">
+
+Insufficient quota errors (402) occur when you do not have remaining credits in your plan.
+
+**Error:** "You exceeded your current quota, please check your plan and billing details"
+
+**Solution:**
+
+- Check your credit balance in the W&B Billing page
+- Purchase more credits or upgrade your plan
+- Request a limit increase from [support](https://wandb.ai/site/contact)
+
+</Accordion>
+</Update>
+
 <Update tags={["Inference"]}>
 <Accordion title="Why does W&B Inference say my country or region is not supported?">
 
@@ -1201,7 +1217,7 @@ This is determined by your IP address location at the time of the API request.
 <Update tags={["Inference"]}>
 <Accordion title="Why isn't W&B Inference available for my personal account?">
 
-Personal accounts don't support W&B Inference. You'll see this 429 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
+Personal accounts don't support W&B Inference. You'll see this 403 error: "W&B Inference isn't available for personal accounts. Please switch to a non-personal account to access W&B Inference."
 
 ## Background
 
@@ -1247,11 +1263,8 @@ If you're having trouble creating a team or switching from a personal account, c
 <Update tags={["Inference"]}>
 <Accordion title="Why am I getting rate limit errors (429) with W&B Inference?">
 
-Rate limit errors (429) occur when you exceed concurrency limits or run out of credits.
-
-## Types of 429 errors
+Rate limit errors (429) occur when you exceed concurrency limits.
 
-### Concurrency limit reached
 **Error:** "Concurrency limit reached for requests"
 
 **Solution:**
@@ -1260,22 +1273,6 @@ Rate limit errors (429) occur when you exceed concurrency limits or run out of c
 - Implement exponential backoff
 - Note: Rate limits apply per W&B project
 
-### Quota exceeded
-**Error:** "You exceeded your current quota, please check your plan and billing details"
-
-**Solution:**
-- Check your credit balance in the W&B Billing page
-- Purchase more credits or upgrade your plan
-- Request a limit increase from support
-
-### Personal account limitation
-**Error:** "W&B Inference isn't available for personal accounts"
-
-**Solution:**
-- Switch to a non-personal account
-- Create a Team to access W&B Inference
-- Personal entities were deprecated in May 2024
-
 ## Best practices to avoid rate limits
 
 1. **Implement retry logic with exponential backoff:**