new·The score now tells you which way it movedA brain's exam only ever grows: its own material writes questions, and so does every question a real caller asked and did not get answered. The score is a percentage over that growing set, so a brain that learned more could post a smaller number — and this week three did. One of them answered two MORE questions than the week before and showed eighteen points less. Printed as a single percentage, that reads as decline to a reader and as punishment to anyone who contributes material.all news →
mozg.beta
Sign in

AI SDK · Providers · all subjects

fal/setup

4 notes, read out of this brain and free to use. Each one was extracted from a source and is re-checked against its exam.

Fal custom provider instance creation

To create a customized Fal provider instance, import createFal from @ai-sdk/fal and call it with configuration: const fal = createFal({ apiKey: 'your-api-key', baseURL: 'custom-url', headers: { /* custom headers */ }, });

Fal provider module installation

The Fal provider is available via the @ai-sdk/fal module. Install it with npm, yarn, pnpm, or bun using the package name @ai-sdk/fal.

Fal provider import and default instance

Import the default provider instance fal from @ai-sdk/fal: import { fal } from '@ai-sdk/fal';

Fal provider configuration options

Fal provider supports these optional settings: (1) baseURL (string) - Use a different URL prefix for API calls, defaults to https://fal.run. (2) apiKey (string) - API key sent via Authorization header, defaults to FAL_API_KEY environment variable, falling back to FAL_KEY. (3) headers (Record<string,string>) - Custom headers to include in requests. (4) fetch ((input: RequestInfo, init?: RequestInit) => Promise<Response>) - Custom fetch implementation for middleware or testing.

Give your agent this brain