Add Gateway provider route to AI SDK

ai-engineering/observe/axiom-ai-sdk-instrumentation.mdx

@@ -21,9 +21,9 @@ Follow the procedure in [Quickstart](/ai-engineering/quickstart) to set up Axiom
 
 ## Instrument AI SDK calls
 
-Axiom AI SDK provides helper functions for Vercel’s [AI SDK](https://ai-sdk.dev/docs) to wrap your existing AI model client.
+Axiom AI SDK provides helper functions for [Vercel AI SDK](https://ai-sdk.dev/docs) to wrap your existing AI model client. The `wrapAISDKModel` function takes an existing AI model object and returns an instrumented version that automatically generates trace data for every call.
 
-The `wrapAISDKModel` function takes an existing AI model object and returns an instrumented version that automatically generates trace data for every call.
+Choose one of the following common Vercel AI SDK providers. For the full list of providers, see the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers).
 
 <Tabs>
 <Tab title="OpenAI">
@@ -124,13 +124,41 @@ The `wrapAISDKModel` function takes an existing AI model object and returns an i
 </Tab>
 </Tabs>
 
+To instrument calls without a Vercel AI SDK provider, use the generic Vercel AI Gateway provider.
+
+<Accordion title="Gateway provider">
+
+To instrument calls without a Vercel AI SDK provider, use the generic Vercel AI Gateway provider. For more information, see the [Vercel documentation](https://ai-sdk.dev/providers/ai-sdk-providers/ai-gateway).
+
+1. Run the following in your terminal to install the Vercel AI SDK:
+
+    ```sh
+    npm i ai
+    ```
+
+1. Create the file `src/shared/openai.ts` with the following content:
+
+    ```ts /src/shared/openai.ts
+    import { createGateway } from 'ai';
+    import { wrapAISDKModel } from 'axiom';
+
+    const gateway = createGateway({
+      apiKey: process.env.OPENAI_API_KEY,
+    });
+
+    // Wrap the model to enable automatic tracing
+    export const gpt4o = wrapAISDKModel(gateway('openai/gpt-4o'));
+    ```
+
+</Accordion>
+
 The rest of the page explains how to work with OpenAI. The process is similar for other LLMs.
 
 ## Add context
 
 The `withSpan` function allows you to add crucial business context to your traces. It creates a parent span around your LLM call and attaches metadata about the `capability` and `step` that you execute.
 
-```typescript /src/app/page.tsx
+```ts /src/app/page.tsx
 import { withSpan } from 'axiom/ai';
 import { generateText } from 'ai';
 import { gpt4o } from '@/shared/openai';
@@ -164,7 +192,7 @@ For many AI capabilities, the LLM call is only part of the story. If your capabi
 
 The `wrapTool` helper takes your tool’s name and its definition and returns an instrumented version. This wrapper creates a dedicated child span for every tool execution, capturing its arguments, output, and any errors.
 
-```typescript /src/app/generate-text/page.tsx
+```ts /src/app/generate-text/page.tsx
 import { tool } from 'ai';
 import { z } from 'zod';
 import { wrapTool } from 'axiom/ai';
@@ -202,7 +230,7 @@ const { text, toolResults } = await generateText({
 
 Example of how all three instrumentation functions work together in a single, real-world example:
 
-```typescript /src/app/page.tsx expandable
+```ts /src/app/page.tsx expandable
 import { withSpan, wrapAISDKModel, wrapTool } from 'axiom/ai';
 import { generateText, tool } from 'ai';
 import { createOpenAI } from '@ai-sdk/openai';