docs(aigw): Prisma AIRS AI Gateway — phases 3, 4 and 5

aigw/api-reference/admin-api/introduction.mdx

@@ -43,19 +43,6 @@ Once your resources are configured, you'll want to measure performance and usage
   </Card>
 </CardGroup>
 
-### User and Workspace Administration
-
-Beyond resources and analytics, you'll need to manage who has access to your AI Gateway environment:
-
-<CardGroup cols={2}>
-  <Card title="Users & Invites" href="/api-reference/admin-api/control-plane/users/retrieve-a-user">
-    Manage user accounts, permissions, and access. Send and manage user invitations.
-  </Card>
-  <Card title="Workspaces & Members" href="/api-reference/admin-api/control-plane/workspaces/create-workspace">
-    Create workspaces and manage team membership and permissions within workspaces.
-  </Card>
-</CardGroup>
-
 ## Authentication Strategy
 
 Now that you understand what the Admin API can do, let's explore how to authenticate your requests. The AI Gateway uses a sophisticated access control system with two types of API keys, each designed for different use cases:
@@ -185,7 +172,7 @@ Every administrative action is recorded with:
 
 This audit trail helps maintain compliance and provides accountability for all administrative changes.
 
-<Card title="Audit Logs Documentation" icon="shield-check" href="https://portkey.ai/docs/product/enterprise-offering/access-control-management#audit-logs">
+<Card title="Audit Logs Documentation" icon="shield-check" href="/aigw/product/enterprise-offering/audit-logs">
   Learn more about the AI Gateway's audit logging capabilities
 </Card>
 
@@ -199,8 +186,8 @@ Now that you understand the Admin API ecosystem, authentication, and permissions
 
 For developers looking to integrate with the Admin API, we provide a complete OpenAPI specification that you can use with your API development tools:
 
-<Card title="OpenAPI Specification" icon="file-code" href="/api-reference/admin-api/open-api-specification">
-  Download the OpenAPI spec for the Admin API
+<Card title="OpenAPI Specification" icon="file-code" href="/aigw/api-reference/inference-api/open-api-specification">
+  A single specification covers both the gateway and the Admin API
 </Card>
 
 ## Need Support?

aigw/api-reference/inference-api/agentic-usage.mdx

@@ -54,7 +54,7 @@ Once installed, your AI coding assistant will have knowledge of:
 - **Caching** — Semantic and simple caching to reduce costs and latency
 - **Fallbacks** — Automatic failover when a provider fails
 - **Load Balancing** — Distribute traffic across multiple providers or API keys
-- **Multi-Provider Routing** — Route requests to 250+ LLMs through a unified API
+- **Multi-Provider Routing** — Route requests to 3,000+ LLMs through a unified API
 - **Error Handling** — Proper retry logic and error handling patterns
 - **Framework Integrations** — Working with LangChain, LlamaIndex, Strands, and Google ADK
 
@@ -66,56 +66,6 @@ After installing the skills, your AI assistant can help you with tasks like:
 
 The assistant will know to use:
 
-<Tabs>
-  <Tab title="Python">
-```python
-from portkey_ai import Portkey
-
-client = Portkey(
-    api_key="YOUR_PORTKEY_API_KEY",
-    config={
-        "strategy": {"mode": "fallback"},
-        "targets": [
-            {
-                "override_params": {"model": "@openai/gpt-4o"}
-            },
-            {
-                "override_params": {"model": "@anthropic/claude-sonnet-4-20250514"}
-            }
-        ]
-    }
-)
-
-response = client.chat.completions.create(
-    messages=[{"role": "user", "content": "Hello!"}]
-)
-```
-  </Tab>
-  <Tab title="TypeScript">
-```typescript
-import Portkey from 'portkey-ai';
-
-const client = new Portkey({
-  apiKey: 'YOUR_PORTKEY_API_KEY',
-  config: {
-    strategy: { mode: 'fallback' },
-    targets: [
-      {
-        overrideParams: { model: '@openai/gpt-4o' }
-      },
-      {
-        overrideParams: { model: '@anthropic/claude-sonnet-4-20250514' }
-      }
-    ]
-  }
-});
-
-const response = await client.chat.completions.create({
-  messages: [{ role: 'user', content: 'Hello!' }]
-});
-```
-  </Tab>
-</Tabs>
 
 **"Add request tracing to my AI Gateway calls"**
 
@@ -156,23 +106,6 @@ const response = await client.chat.completions.create({
 
 **"Enable semantic caching for my LLM requests"**
 
-```python
-client = Portkey(
-    api_key="YOUR_PORTKEY_API_KEY",
-    config={
-        "cache": {
-            "mode": "semantic",  # or "simple" for exact match
-            "max_age": 3600      # TTL in seconds
-        }
-    }
-)
-
-# Similar queries return cached responses
-response = client.chat.completions.create(
-    model="@openai/gpt-4o",
-    messages=[{"role": "user", "content": "What is the capital of France?"}]
-)
-```
 
 ## Installation Options
 
@@ -245,12 +178,6 @@ The skill source is available at: [github.com/portkey-ai/skills](https://github.
 Contributions and feedback are welcome.
 
 <CardGroup cols={2}>
-  <Card title="Python SDK Docs" icon="python" href="/api-reference/sdk/python">
-    Full Python SDK documentation
-  </Card>
-  <Card title="TypeScript SDK Docs" icon="js" href="/api-reference/sdk/node">
-    Full TypeScript SDK documentation
-  </Card>
   <Card title="Skills Repository" icon="github" href="https://github.com/portkey-ai/skills">
     View the skills source on GitHub
   </Card>

aigw/api-reference/inference-api/authentication.mdx

@@ -14,54 +14,18 @@ Based on your access level, you might see the relevant permissions on the API ke
     You can also authenticate the AI Gateway using JWT Tokens. Learn more here
 </Card>
 
-## Authentication with SDKs
+## Using Your API Key
 
-### AI Gateway SDKs
+### REST API
 
 <Tabs>
-  <Tab title="NodeJS SDK">
-```ts
-import Portkey from 'portkey-ai'
-
-const portkey = new Portkey({
-    apiKey: "PORTKEY_API_KEY", // Replace with your actual API key
-    provider: "@openai-prod"   // Optional: AI Provider slug from Model Catalog
-})
-
-const chatCompletion = await portkey.chat.completions.create({
-    messages: [{ role: 'user', content: 'Say this is a test' }],
-    model: 'gpt-4o',
-});
-
-console.log(chatCompletion.choices);
-```
-  </Tab>
-  <Tab title="Python SDK">
-```python
-from portkey_ai import Portkey
-
-client = Portkey(
-    api_key="PORTKEY_API_KEY",  # Replace with your actual API key
-    provider="@openai-prod"    # Optional: AI Provider slug from Model Catalog
-)
-
-chat_completion = client.chat.completions.create(
-    messages=[{"role": "user", "content": "Say this is a test"}],
-    model='gpt-4o'
-)
-
-print(chat_completion.choices[0].message["content"])
-```
-
-  </Tab>
   <Tab title="cURL">
 ```sh
 curl https://aigw.portkey.ai/v1/chat/completions \
   -H "Content-Type: application/json" \
   -H "Authorization: Bearer $PORTKEY_API_KEY" \
-  -H "x-portkey-provider: @openai-prod" \
   -d '{
-    "model": "gpt-4o",
+    "model": "@openai-prod/gpt-4o",
     "messages": [
       { "role": "system", "content": "You are a helpful assistant." },
       { "role": "user", "content": "Hello!" }
@@ -76,30 +40,25 @@ curl https://aigw.portkey.ai/v1/chat/completions \
 When integrating the AI Gateway through the OpenAI SDK, modify the base URL and add the `Authorization` header for authentication. Here's an example of how to do it:
 
 <Info>
-We use the `createHeaders` helper function from the AI Gateway SDK here to easily create AI Gateway headers.
-
-You can pass the raw headers (`x-portkey-api-key`, `x-portkey-provider`) directly in the `defaultHeaders` param as well.
+Gateway headers go in the SDK's `defaultHeaders` / `default_headers` parameter. Most requests
+need only `x-portkey-provider`, and even that is unnecessary when you prefix the model with the
+provider slug — `"model": "@openai-prod/gpt-4o"`.
 </Info>
 
 <Tabs>
   <Tab title="NodeJS">
 ```js
 import OpenAI from 'openai';
-import { PORTKEY_GATEWAY_URL, createHeaders } from 'portkey-ai'
 
 const openai = new OpenAI({
-  apiKey: 'OPENAI_API_KEY',
-  baseURL: PORTKEY_GATEWAY_URL,
-  defaultHeaders: createHeaders({
-    provider: "openai",
-    apiKey: "PORTKEY_API_KEY"
-  })
+  apiKey: "PORTKEY_API_KEY",
+  baseURL: "https://aigw.portkey.ai/v1",
 });
 
 async function main() {
   const chatCompletion = await openai.chat.completions.create({
     messages: [{ role: 'user', content: 'Say this is a test' }],
-    model: 'gpt-4o',
+    model: '@openai/gpt-4o',
   });
 
   console.log(chatCompletion.choices);
@@ -112,18 +71,14 @@ main();
   <Tab title="Python">
 ```python
 from openai import OpenAI
-from portkey_ai import PORTKEY_GATEWAY_URL, createHeaders
 
 openai_client = OpenAI(
-    base_url=PORTKEY_GATEWAY_URL,
-    default_headers=createHeaders(
-        api_key="PORTKEY-API-KEY",
-        provider="openai"
-    )
+    api_key="PORTKEY_API_KEY",
+    base_url="https://aigw.portkey.ai/v1",
 )
 response = openai_client.chat.completions.create(
         messages=[{'role': 'user', 'content': 'Say this is a test'}],
-        model='gpt-4bo'
+        model='@openai/gpt-4o'
 )
 ```
   </Tab>