feat: improve aig getting started, fix redirects

Author: palashgo

public/__redirects

@@ -163,11 +163,11 @@
 /ai-gateway/integration/vercel-ai-sdk/ /ai-gateway/integrations/vercel-ai-sdk/ 301
 /ai-gateway/integration/aig-workers-ai-binding/ /ai-gateway/integrations/aig-workers-ai-binding/ 301
 /ai-gateway/integration/ /ai-gateway/integrations/ 301
-/ai-gateway/providers/open-router/ /ai-gateway/providers/openrouter/ 301
-/ai-gateway/providers/universal/ /ai-gateway/universal/ 301
-/ai-gateway/configuration/websockets-api/ /ai-gateway/websockets-api/ 301
-/ai-gateway/configuration/websockets-api/non-realtime-api/ /ai-gateway/websockets-api/non-realtime-api/ 301
-/ai-gateway/configuration/websockets-api/realtime-api/ /ai-gateway/websockets-api/realtime-api/ 301
+/ai-gateway/providers/open-router/ /ai-gateway/usage/providers/openrouter/ 301
+/ai-gateway/providers/universal/ /ai-gateway/usage/universal/ 301
+/ai-gateway/configuration/websockets-api/ /ai-gateway/usage/websockets-api/ 301
+/ai-gateway/configuration/websockets-api/non-realtime-api/ /ai-gateway/usage/websockets-api/non-realtime-api/ 301
+/ai-gateway/configuration/websockets-api/realtime-api/ /ai-gateway/usage/websockets-api/realtime-api/ 301
 /ai-gateway/configuration/caching/ /ai-gateway/features/caching/ 301
 /ai-gateway/configuration/rate-limiting/ /ai-gateway/features/rate-limiting/ 301
 /ai-gateway/configuration/custom-metadata/ /ai-gateway/observability/custom-metadata/ 301

src/content/docs/ai-gateway/configuration/authentication.mdx

@@ -1,6 +1,6 @@
 ---
 pcx_content_type: configuration
-title: Authentication
+title: Authenticated Gateway
 sidebar:
   order: 7
 head: []

src/content/docs/ai-gateway/configuration/bring-your-own-keys.mdx

@@ -22,9 +22,8 @@ The keys are stored securely with [Secret Store](/secrets-store/) and allows for
 
 ### Prerequisites
 
-- An active Cloudflare account with AI Gateway enabled
-- Valid API keys for the AI providers you want to use
-- Appropriate permissions to manage AI Gateway settings
+- Ensure your gateway is [authenticated](/ai-gateway/configuration/authentication/)
+- Appropriate permissions to create and deploy secrets on Secret Store
 
 ### Configure API keys
 
@@ -44,7 +43,7 @@ The keys are stored securely with [Secret Store](/secrets-store/) and allows for
 Once you've configured your API keys in the dashboard:
 
 1. **Remove API keys from your code**: Delete any hardcoded API keys or environment variables
-2. **Update request headers**: Remove authorization headers from your requests
+2. **Update request headers**: Remove provider authorization headers from your requests, you still need to pass `cf-aig-authorization`
 3. **Test your integration**: Verify that requests work without including API keys
 
 ## Example

src/content/docs/ai-gateway/features/dynamic-routing/index.mdx

@@ -10,6 +10,10 @@ sidebar:
 
 import { CardGrid, LinkTitleCard, YouTube } from "~/components";
 
+:::caution
+Dynamic routing is in closed beta. Request for access
+:::
+
 ## Introduction
 
 Dynamic routing enables you to create request routing flows through a **visual interface** or a **JSON-based configuration**. Instead of hard-coding a single model, with Dynamic Routing you compose a small flow that evaluates conditions, enforces quotas, and chooses models with fallbacks. You can iterate without touching application code—publish a new route version and you’re done. With dynamic routing, you can easily implement advanced use cases such as

src/content/docs/ai-gateway/get-started.mdx

@@ -13,86 +13,82 @@ import {
 	Render,
 	TabItem,
 	Tabs,
+	Badge,
 } from "~/components";
 
-In this guide, you will learn how to create your first AI Gateway. You can create multiple gateways to control different applications.
+In this guide, you will learn how to create and use your first AI Gateway.
 
-## Prerequisites
+<Render file="create-gateway" />
 
-Before you get started, you need a Cloudflare account.
+### Authenticated gateway
 
-<LinkButton variant="primary" href="https://dash.cloudflare.com/sign-up">
-	Sign up
-</LinkButton>
+When you enable authentication on gateway each request is required to include a valid cloudflare token, adding an extra layer of security. We recommend using an authenticated gateway when storing logs to prevent unauthorized access and protect against invalid requests that can inflate log storage usage and make it harder to find the data you need. [Learn more](/ai-gateway/configuration/authentication/).
 
-## Create gateway
+## Provider Authentication
 
-Then, create a new AI Gateway.
+Authenticate with your upstream provider using one of the following options:
 
-<Render file="create-gateway" />
+- **BYOK (Store Keys):** Store your credentials in Cloudflare and AI Gateway will include them at runtime. See [BYOK](/ai-gateway/configuration/bring-your-own-keys/).
+- **Request headers:** Include your provider key in the request headers as you normally would (e.g., `Authorization: Bearer <PROVIDER_API_KEY>`).
+
+## Integration Options
 
-## Choosing gateway authentication
+### Unified API (OpenAI-Compatible) Endpoint
 
-When setting up a new gateway, you can choose between an authenticated and unauthenticated gateway. Enabling an authenticated gateway requires each request to include a valid authorization token, adding an extra layer of security. We recommend using an authenticated gateway when storing logs to prevent unauthorized access and protect against invalid requests that can inflate log storage usage and make it harder to find the data you need. Learn more about setting up an [Authenticated Gateway](/ai-gateway/configuration/authentication/).
+<Badge text="recommended" variant="success" size="small" />
+<br />
+<br />
+
+The easiest way to get started with AI Gateway is through our OpenAI-compatible `/chat/completions` endpoint. This allows you to use existing OpenAI SDKs and tools with minimal code changes while gaining access to multiple AI providers.
+
+```txt
+https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions
+```
 
-## Send a request
+**Key benefits:**
 
-#### Chat completions endpoint
+- Drop-in replacement for OpenAI API
+- Works with existing OpenAI SDKs and other OpenAI compliant clients
+- Switch between providers by changing the `model` parameter
+- Dynamic Routing - Define complex routing scenarios requiring conditional logic, conduct A/B tests, set rate / budget limits etc
 
-<Tabs syncKey="aiGatewayGetStarted">
-<TabItem label="OpenAI SDK">
+#### Example:
 
-```js
+```javascript
 import OpenAI from "openai";
+
 const client = new OpenAI({
-	apiKey: "YOUR_PROVIDER_API_KEY", // Provider API key
-	// NOTE: the OpenAI client automatically adds /chat/completions to the end of the URL, you should not add it yourself.
+	apiKey: "YOUR_PROVIDER_API_KEY",
 	baseURL:
 		"https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat",
 });
 
+// Use different providers by changing the model parameter
 const response = await client.chat.completions.create({
-	model: "google-ai-studio/gemini-2.0-flash",
-	messages: [{ role: "user", content: "What is Cloudflare?" }],
+	model: "google-ai-studio/gemini-2.0-flash", // or "openai/gpt-4o", "anthropic/claude-3-haiku"
+	messages: [{ role: "user", content: "Hello, world!" }],
 });
-console.log(response.choices[0].message.content);
 ```
 
-</TabItem>
-<TabItem label="AI Gateway API">
-```bash
-curl -X POST https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions \
-  --header 'Authorization: Bearer {GOOGLE_GENERATIVE_AI_API_KEY}' \
-  --header 'Content-Type: application/json' \
-  --data '{
-    "model": "google-ai-studio/gemini-2.5-flash",
-    "messages": [
-      {
-        "role": "user",
-        "content": "What is Cloudflare?"
-      }
-    ]
-  }'
-````
-
-</TabItem>
-</Tabs>
-
-There are multiple other ways to send a request to AI Gateway check out the [usage](/ai-gateway/usage/) section for more details.
+[Learn more about OpenAI compatibility →](/ai-gateway/usage/chat-completion/)
 
-## View analytics
+### Provider-Specific Endpoints
 
-Now that you have sent your first request to AI Gateway, you can view analytics for requests going through your gateway.
+For direct integration with specific AI providers, use dedicated endpoints that maintain the original provider's API schema while adding AI Gateway features.
 
-<Render file="analytics-overview" /> <br />
-
-<Render file="analytics-dashboard" />
-
-:::note[Note]
+```txt
+https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/{provider}
+```
 
-The cost metric is an estimation based on the number of tokens sent and received in requests. While this metric can help you monitor and predict cost trends, refer to your provider's dashboard for the most accurate cost details.
+**Available providers:**
 
-:::
+- [OpenAI](/ai-gateway/usage/providers/openai/) - GPT models and embeddings
+- [Anthropic](/ai-gateway/usage/providers/anthropic/) - Claude models
+- [Google AI Studio](/ai-gateway/usage/providers/google-ai-studio/) - Gemini models
+- [Workers AI](/ai-gateway/usage/providers/workersai/) - Cloudflare's inference platform
+- [AWS Bedrock](/ai-gateway/usage/providers/bedrock/) - Amazon's managed AI service
+- [Azure OpenAI](/ai-gateway/usage/providers/azureopenai/) - Microsoft's OpenAI service
+- [and more...](/ai-gateway/usage/providers/)
 
 ## Next steps
 

src/content/docs/ai-gateway/usage/chat-completion.mdx

@@ -1,5 +1,5 @@
 ---
-title: OpenAI Compatibility
+title: Unified API (OpenAI compat)
 pcx_content_type: reference
 tags:
   - AI

src/content/docs/ai-gateway/usage/index.mdx

@@ -3,101 +3,8 @@ title: Using AI Gateway
 pcx_content_type: get-started
 sidebar:
   order: 3
+  group:
+    hideIndex: true
 ---
 
-import { Render, Badge } from "~/components";
-
-AI Gateway provides multiple ways to integrate with AI providers, offering flexibility and advanced features like caching, analytics, rate limiting, and fallbacks. Choose the integration method that best fits your needs.
-
-## Integration Options
-
-### OpenAI-Compatible Endpoint <Badge text="recommended" variant="success" size="small" />
-
-The easiest way to get started with AI Gateway is through our OpenAI-compatible `/chat/completions` endpoint. This allows you to use existing OpenAI SDKs and tools with minimal code changes while gaining access to multiple AI providers.
-
-```txt
-https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat/chat/completions
-```
-
-**Key benefits:**
-
-- Drop-in replacement for OpenAI API
-- Works with existing OpenAI SDKs and other OpenAI compliant clients
-- Switch between providers by changing the `model` parameter
-- No schema modifications required
-- Dynamic Routing - Define complex routing scenarios requiring conditional logic, conduct A/B tests, set rate / budget limits etc
-
-[Learn more about OpenAI compatibility →](/ai-gateway/usage/chat-completion/)
-
-### Provider-Specific Endpoints
-
-For direct integration with specific AI providers, use dedicated endpoints that maintain the original provider's API schema while adding AI Gateway features.
-
-```txt
-https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/{provider}
-```
-
-**Available providers:**
-
-- [OpenAI](/ai-gateway/usage/providers/openai/) - GPT models and embeddings
-- [Anthropic](/ai-gateway/usage/providers/anthropic/) - Claude models
-- [Google AI Studio](/ai-gateway/usage/providers/google-ai-studio/) - Gemini models
-- [Workers AI](/ai-gateway/usage/providers/workersai/) - Cloudflare's inference platform
-- [AWS Bedrock](/ai-gateway/usage/providers/bedrock/) - Amazon's managed AI service
-- [Azure OpenAI](/ai-gateway/usage/providers/azureopenai/) - Microsoft's OpenAI service
-- [and more...](/ai-gateway/usage/providers/)
-
-### WebSockets API <Badge text="beta" variant="tip" size="small" />
-
-For real-time applications requiring persistent connections, AI Gateway offers WebSockets support. This enables streaming responses and continuous communication with AI providers.
-
-```txt
-wss://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/
-```
-
-**Key benefits:**
-
-- Single persistent connection
-- Real-time streaming responses
-- Support for providers without native WebSocket support
-- Reduced connection overhead
-
-[Learn more about WebSockets API →](/ai-gateway/usage/websockets-api/)
-
-## Quick Start Examples
-
-### Using OpenAI SDK with Multiple Providers
-
-```javascript
-import OpenAI from "openai";
-
-const client = new OpenAI({
-	apiKey: "YOUR_PROVIDER_API_KEY",
-	baseURL:
-		"https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/compat",
-});
-
-// Use different providers by changing the model parameter
-const response = await client.chat.completions.create({
-	model: "google-ai-studio/gemini-2.0-flash", // or "openai/gpt-4o", "anthropic/claude-3-haiku"
-	messages: [{ role: "user", content: "Hello, world!" }],
-});
-```
-
-## Choosing the Right Integration
-
-| Use Case                        | Recommended Approach        |
-| ------------------------------- | --------------------------- |
-| **Getting started quickly**     | OpenAI-Compatible Endpoint  |
-| **Existing OpenAI integration** | OpenAI-Compatible Endpoint  |
-| **Provider-specific features**  | Provider-Specific Endpoints |
-| **Real-time/streaming apps**    | WebSockets API              |
-
-## Next Steps
-
-1. **[Set up your first gateway](/ai-gateway/get-started/)** if you haven't already
-2. **Choose your integration method** based on your requirements
-3. **Configure advanced features** like [caching](/ai-gateway/features/caching/), [rate limiting](/ai-gateway/features/rate-limiting/), and [analytics](/ai-gateway/observability/)
-4. **Explore provider-specific documentation** for detailed implementation guides
-
-For more advanced configuration options, see the [Configuration](/ai-gateway/configuration/) section.
+##

src/content/docs/ai-gateway/usage/providers/index.mdx

@@ -1,6 +1,6 @@
 ---
 pcx_content_type: navigation
-title: Model providers
+title: Provider specific
 sidebar:
   group:
     hideIndex: true

src/content/partials/ai-gateway/create-gateway.mdx

@@ -2,11 +2,14 @@
 {}
 ---
 
-import { TabItem, Tabs } from "~/components";
+import { TabItem, Tabs, LinkButton } from "~/components";
 
-<Tabs syncKey="dashPlusAPI"> <TabItem label="Dashboard">
+<Tabs syncKey="dashPlusAPI"> 
+<TabItem label="Dashboard">
 
-To set up an AI Gateway in the dashboard:
+<LinkButton href="https://dash.cloudflare.com/?to=/:account/ai/ai-gateway#create">
+	Create a Gateway
+</LinkButton>
 
 1. Log into the [Cloudflare dashboard](https://dash.cloudflare.com/) and select your account.
 2. Go to **AI** > **AI Gateway**.
@@ -19,7 +22,6 @@ To set up an AI Gateway in the dashboard:
 To set up an AI Gateway using the API:
 
 1. [Create an API token](/fundamentals/api/get-started/create-token/) with the following permissions:
-
    - `AI Gateway - Read`
    - `AI Gateway - Edit`