diff 2

Author: vrushankportkey

integrations/llms/vertex-ai/batches.mdx

@@ -18,7 +18,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER", # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER", 
     vertex_storage_bucket_name="your_bucket_name", # Specify the GCS bucket name
     provider_file_name="your_file_name.jsonl", # Specify the file name in GCS
     provider_model="gemini-1.5-flash-001" # Specify the model to use
@@ -41,7 +41,7 @@ import * as fs from 'fs';
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER",   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER",   
     vertexStorageBucketName: "your_bucket_name", // Specify the GCS bucket name
     providerFileName: "your_file_name.jsonl", // Specify the file name in GCS
     providerModel: "gemini-1.5-flash-001" // Specify the model to use
@@ -137,7 +137,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # Create a batch inference job
@@ -158,7 +158,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {
@@ -248,7 +248,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # List all batch jobs
@@ -266,7 +266,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {
@@ -346,7 +346,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # Retrieve a specific batch job
@@ -364,7 +364,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {

integrations/llms/vertex-ai/files.mdx

@@ -15,7 +15,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER",   # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER",   
     vertex_storage_bucket_name="your_bucket_name", # Specify the GCS bucket name
     provider_file_name="your_file_name.jsonl", # Specify the file name in GCS
     provider_model="gemini-1.5-flash-001" # Specify the model to use
@@ -37,7 +37,7 @@ import * as fs from 'fs';
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER",   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER",   
     vertexStorageBucketName: "your_bucket_name", // Specify the GCS bucket name
     providerFileName: "your_file_name.jsonl", // Specify the file name in GCS
     providerModel: "gemini-1.5-flash-001" // Specify the model to use
@@ -135,7 +135,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER"   # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER"   
 )
 
 file = portkey.files.retrieve(file_id="file_id")
@@ -150,7 +150,7 @@ import { Portkey } from 'portkey-ai';
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 const getFile = async () => {
@@ -224,7 +224,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER"   # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER"   
 )
 
 file_content = portkey.files.content(file_id="file_id")
@@ -239,7 +239,7 @@ import { Portkey } from 'portkey-ai';
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 const getFileContent = async () => {

integrations/llms/vertex-ai/fine-tuning.mdx

@@ -13,7 +13,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER", # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER", 
     vertex_storage_bucket_name="your_bucket_name", # Specify the GCS bucket name
     provider_file_name="your_file_name.jsonl", # Specify the file name in GCS
     provider_model="gemini-1.5-flash-001" # Specify the model to fine-tune
@@ -36,7 +36,7 @@ import * as fs from 'fs';
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER",   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER",   
     vertexStorageBucketName: "your_bucket_name", // Specify the GCS bucket name
     providerFileName: "your_file_name.jsonl", // Specify the file name in GCS
     providerModel: "gemini-1.5-flash-001" // Specify the model to fine-tune
@@ -132,7 +132,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # Create a fine-tuning job
@@ -155,7 +155,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {
@@ -251,7 +251,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # List all fine-tuning jobs
@@ -269,7 +269,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {
@@ -347,7 +347,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # Retrieve a specific fine-tuning job
@@ -365,7 +365,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {
@@ -443,7 +443,7 @@ from portkey_ai import Portkey
 # Initialize the Portkey client
 portkey = Portkey(
     api_key="PORTKEY_API_KEY", # Replace with your Portkey API key
-    provider="@VERTEX_PROVIDER" # Add your Vertex virtual key
+    provider="@VERTEX_PROVIDER" 
 )
 
 # Cancel a fine-tuning job
@@ -461,7 +461,7 @@ import { Portkey } from "portkey-ai";
 // Initialize the Portkey client
 const portkey = Portkey({
     apiKey: "PORTKEY_API_KEY",  // Replace with your Portkey API key
-    provider:"@VERTEX_PROVIDER"   // Add your Vertex virtual key
+    provider:"@VERTEX_PROVIDER"   
 });
 
 (async () => {

product/ai-gateway/request-timeouts.mdx

@@ -26,16 +26,14 @@ Set request timeout while instantiating your Portkey client or if you're using t
 ```js
 import Portkey from 'portkey-ai';
 
-// Construct a client with a virtual key
 const portkey = new Portkey({
     apiKey: "PORTKEY_API_KEY",
-    provider:"@PROVIDER",
     requestTimeout: 3000
 })
 
 const chatCompletion = await portkey.chat.completions.create({
     messages: [{ role: 'user', content: 'Say this is a test' }],
-    model: 'gpt-4o-mini',
+    model: '@openai/gpt-4o-mini',
 });
 
 console.log(chatCompletion.choices);
@@ -46,16 +44,14 @@ console.log(chatCompletion.choices);
 ```py
 from portkey_ai import Portkey
 
-# Construct a client with a virtual key
 portkey = Portkey(
     api_key="PORTKEY_API_KEY",
-    provider="@PROVIDER",
     request_timeout=3000
 )
 
 completion = portkey.chat.completions.create(
     messages = [{ "role": 'user', "content": 'Say this is a test' }],
-    model = 'gpt-4o-mini'
+    model = '@openai/gpt-4o-mini'
 )
 ```
   </Tab>
@@ -65,10 +61,9 @@ completion = portkey.chat.completions.create(
 curl "https://api.portkey.ai/v1/chat/completions" \
   -H "Content-Type: application/json" \
   -H "x-portkey-api-key: $PORTKEY_API_KEY" \
-  -H "x-portkey-provider: openai-virtual-key" \
   -H "x-portkey-request-timeout:5000" \
   -d '{
-    "model": "gpt-4o-mini",
+    "model": "@openai/gpt-4o-mini",
     "messages": [{"role": "user", "content": "Hello!"}]
   }'
 ```
@@ -93,8 +88,8 @@ For a 10-second timeout, it will be:
   "strategy": { "mode": "fallback" },
   "request_timeout": 10000,
   "targets": [
-    { "provider":"@open-ai-xxx" },
-    { "provider":"@azure-open-ai-xxx" }
+    { "provider":"@openai" },
+    { "provider":"@azure-openai" }
   ]
 }
 ```
@@ -107,8 +102,8 @@ Here, the request timeout of 10 seconds will be applied to \* **all**\* the targ
 {
   "strategy": { "mode": "fallback" },
   "targets": [
-    { "provider":"@open-ai-xxx", "request_timeout": 10000, },
-    { "provider":"@azure-open-ai-xxx", "request_timeout": 2000,}
+    { "provider":"@openai", "request_timeout": 10000, },
+    { "provider":"@azure-openai", "request_timeout": 2000,}
   ]
 }
 ```
@@ -132,17 +127,17 @@ Nested target objects inherit the top-level timeout, with the option to override
       "request_timeout": 5000,
       "targets": [
         {
-          "provider:"@open-ai-1-1"
+          "provider:"@openai"
         },
         {
-          "provider":"@open-ai-1-2",
+          "provider":"@azure-openai",
           "request_timeout": 10000
         }
       ],
       "weight": 1
     },
     {
-      "provider":"@azure-open-ai-1",
+      "provider":"@azure-openai",
       "weight": 1
     }
   ]
@@ -151,9 +146,9 @@ Nested target objects inherit the top-level timeout, with the option to override
 
 1. We've set a global timeout of **2s** at line #3
 2. The first target has a nested fallback strategy, with a top level request timeout of **5s** at line #7
-3. The first virtual key (at line #10), the **target-level** timeout of **5s** will be applied
-4. For the second virtual key (i.e. `open-ai-1-2`), there is a timeout override, set at **10s**, which will be applied only to this target
-5. For the last target (i.e. virtual key `azure-open-ai-1`), the top strategy-level timeout of **2s** will be applied
+3. The first provider (at line #10), the **target-level** timeout of **5s** will be applied
+4. For the second provider (i.e. `azure-openai`), there is a timeout override, set at **10s**, which will be applied only to this target
+5. For the last provider (i.e. provider `azure-openai`), the top strategy-level timeout of **2s** will be applied
 
 ## Handling Request Timeouts
 
@@ -168,8 +163,8 @@ Portkey issues a standard **408 error** for timed-out requests. You can leverage
     "on_status_codes": [408]
   },
   "targets": [
-    { "provider":"@open-ai-xxx", "request_timeout": 2000, },
-    { "provider":"@azure-open-ai-xxx"}
+    { "provider":"@openai", "request_timeout": 2000, },
+    { "provider":"@azure-openai"}
   ]
 }
 ```
@@ -182,7 +177,7 @@ Here, fallback from OpenAI to Azure OpenAI will only be triggered if the first r
 {
     "request_timeout": 1000,
     "retry": { "attempts": 3, "on_status_codes": [ 408 ] },
-    "provider":"@open-ai-xxx"
+    "provider":"@openai"
 }
 ```
 

product/ai-gateway/strict-open-ai-compliance.mdx

@@ -21,8 +21,8 @@ To get those fields in the response, you can do one of the following:
     from portkey_ai import Portkey
 
     portkey = Portkey(
-        api_key="PORTKEY_API_KEY",  # Replace with your Portkey API key
-        provider="@PROVIDER",   # Replace with your virtual key
+        api_key="PORTKEY_API_KEY",
+        provider="@PROVIDER", 
         strict_open_ai_compliance=False
     )
     ```
@@ -32,8 +32,8 @@ To get those fields in the response, you can do one of the following:
     import Portkey from 'portkey-ai'
 
     const portkey = new Portkey({
-        apiKey: "PORTKEY_API_KEY", // defaults to process.env["PORTKEY_API_KEY"]
-        provider:"@PROVIDER", // Your Virtual Key
+        apiKey: "PORTKEY_API_KEY",
+        provider:"@PROVIDER",
         strictOpenAiCompliance: false
     })
     ```

product/ai-gateway/virtual-keys/budget-limits.mdx

@@ -33,7 +33,7 @@ And you can set both these limtis for each workspace.
 > * Budget limits apply until exhausted or reset
 > * Budget limits are applied only to requests made after the limit is set; they do not apply retroactively
 > * Once set, budget limits **cannot be edited** by any organization member
-> * Budget limits work for **all providers** available on Portkey and apply to **all organization members** who use the virtual key
+> * Budget limit feature is available for **all LLMs** available on Portkey and will apply to **all members/workspaces** who have permission to use it.
 
 ## Alert Thresholds
 
@@ -71,7 +71,7 @@ You can track your spending and token usage for any specific provider by navigat
 
 ## Pricing Support and Limitations
 
-Budget limits currently apply to all providers and models for which Portkey has pricing support. If a specific request log shows `0 cents` in the COST column, it means that Portkey does not currently track pricing for that model, and it will not count towards the virtual key's budget limit.
+Budget limits currently apply to all providers and models for which Portkey has pricing support. If a specific request log shows `0 cents` in the COST column, it means that Portkey does not currently track pricing for that model, and it will not count towards the providers's budget limit.
 
 For token-based budgets, Portkey tracks both input and output tokens across all supported models.
 

product/ai-gateway/virtual-keys/rate-limits.mdx

@@ -31,10 +31,10 @@ Set a maximum number of tokens that can be consumed within a specified time peri
 >
 > * Rate limits can be set as either request-based or token-based
 > * Time intervals can be configured as per minute, per hour, or per day
-> * Setting the limit to 0 disables the virtual key
+> * Setting the limit to 0 disables the provider
 > * Rate limits apply immediately after being set
-> * Once set, budget limits **cannot be edited** by any organization member
-> * Rate limits work for **all providers** available on Portkey and apply to **all organization members** who use the virtual key
+> * Once set, rate limits **cannot be edited** by any organization member
+> * Rate limits work for **all providers** available on Portkey and apply to **all organization members** who use the provider
 > * After a rate limit is reached, requests will be rejected until the time period resets
 
 ## Rate Limit Intervals