Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 13 additions & 1 deletion src/content/docs/ai-gateway/integrations/vercel-ai-sdk.mdx
Original file line number Diff line number Diff line change
Expand Up @@ -40,13 +40,25 @@ const anthropic = createAnthropic({
If you're using the Google AI Studio provider in AI SDK, you need to append `/v1beta` to your Google AI Studio-compatible AI Gateway URL to avoid errors. The `/v1beta` path is required because Google AI Studio's API includes this in its endpoint structure, and the AI SDK sets the model name separately. This ensures compatibility with Google's API versioning.

```typescript
import { createGoogleGenerativeAI } from '@ai-sdk/google';
import { createGoogleGenerativeAI } from "@ai-sdk/google";

const google = createGoogleGenerativeAI({
baseURL: `https://gateway.ai.cloudflare.com/v1/{account_id}/{gateway_id}/google-ai-studio/v1beta`,
});
```

### Retrieve `log id` from AI SDK

You can access the AI Gateway `log id` from the response headers when invoking the SDK.

```typescript
const result = await generateText({
model: anthropic("claude-3-sonnet-20240229"),
messages: [],
});
console.log(result.response.headers["cf-aig-log-id"]);
```

### Other providers

For other providers that are not listed above, you can follow a similar pattern by creating a custom instance for any AI provider, and passing your AI Gateway URL. For help finding your provider-specific AI Gateway URL, refer to the [Supported providers page](/ai-gateway/providers).
Loading