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

baseten/options

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.

Baseten provider customization options

The Baseten provider supports the following optional settings when using createBaseten(): baseURL (string) - Use a different URL prefix for API calls, defaults to `https://inference.baseten.co/v1`. apiKey (string) - API key for Authorization header, defaults to `BASETEN_API_KEY` environment variable. modelURL (string) - Custom model URL for specific models (chat or embeddings), uses default Model APIs if not provided. headers (Record<string,string>) - Custom headers to include in requests. performanceClient (PerformanceClient constructor) - Opt in to Baseten's native performance client for embeddings for client-side batching and request hedging, pass constructor from `@basetenlabs/performance-client`. fetch (function) - Custom fetch implementation.

Baseten OpenAI-compatible endpoints for chat

For models deployed with Baseten's OpenAI-compatible endpoints, use the `/sync/v1` endpoint pattern. Example URL: `https://model-{MODEL_ID}.api.baseten.co/sync/v1`. When using a custom modelURL, no modelId is needed in the baseten() call. Example: `const baseten = createBaseten({ modelURL: 'https://model-{MODEL_ID}.api.baseten.co/sync/v1' }); const model = baseten();`

Baseten native performance client for embeddings

Baseten publishes `@basetenlabs/performance-client`, a native client that adds client-side batching and request hedging on top of server-side dynamic batching. It is not installed by default as it is a native addon that cannot load in edge runtimes. To use it, install separately with `npm i @basetenlabs/performance-client` and pass the PerformanceClient constructor to the provider instance.

Baseten performance client usage example

Example of using native performance client: `import { createBaseten } from '@ai-sdk/baseten'; import { PerformanceClient } from '@basetenlabs/performance-client'; const baseten = createBaseten({ modelURL: 'https://model-{MODEL_ID}.api.baseten.co/environments/production/sync', performanceClient: PerformanceClient });`

Give your agent this brain