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

apertis/setup

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

Apertis package installation

Install the Apertis AI SDK provider package using @apertis/ai-sdk-provider.

Apertis provider import methods

The Apertis provider can be imported as a default instance using 'import { apertis } from "@apertis/ai-sdk-provider"' or created as a custom instance using 'createApertis({ apiKey: process.env.APERTIS_API_KEY })'.

Apertis API key configuration

The Apertis API key is set via the APERTIS_API_KEY environment variable when creating a custom instance, or obtained from the Apertis Dashboard at https://apertis.ai/token.

Apertis generateText example

Example generating text with Apertis: import { apertis } from '@apertis/ai-sdk-provider'; import { generateText } from 'ai'; const { text } = await generateText({ model: apertis('gpt-5.2'), prompt: 'Explain quantum computing in simple terms.' });

Apertis streamText example

Example streaming text with Apertis: import { apertis } from '@apertis/ai-sdk-provider'; import { streamText } from 'ai'; const { textStream } = await streamText({ model: apertis('claude-sonnet-4.5'), prompt: 'Write a haiku about programming.' }); for await (const chunk of textStream) { process.stdout.write(chunk); }

Apertis embed example

Example generating embeddings with Apertis: import { apertis } from '@apertis/ai-sdk-provider'; import { embed } from 'ai'; const { embedding } = await embed({ model: apertis.textEmbeddingModel('text-embedding-3-small'), value: 'Hello world' });

Give your agent this brain