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

cencori/capabilities

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

Cencori capabilities

Cencori supports generateText and streamText for text generation. Tool calling is supported with all compatible models. Models can be used with Next.js route handlers and the useChat React hook.

Cencori tool calling support

Cencori supports tool calling with compatible models. Tools are defined using the tool() function with description, inputSchema (using Zod), and execute function. Example: tool({ description: 'Get the weather for a location', inputSchema: z.object({ location: z.string().describe('The city and state') }), execute: async ({ location }) => { return { temperature: 72, condition: 'sunny', location }; } })

Cencori generateText example

Example of using Cencori with generateText: import { cencori } from 'cencori/vercel'; import { generateText } from 'ai'; const { text } = await generateText({ model: cencori('gpt-4o'), prompt: 'What is Cencori?' }); console.log(text);

Cencori streamText example

Example of using Cencori with streamText: import { cencori } from 'cencori/vercel'; import { streamText } from 'ai'; const result = streamText({ model: cencori('claude-3-5-sonnet'), prompt: 'Write a short story about AI safety.' }); for await (const chunk of result.textStream) { console.log(chunk); }

Cencori Next.js route handler example

Example of using Cencori in a Next.js POST route handler: import { cencori } from 'cencori/vercel'; import { streamText } from 'ai'; export async function POST(req: Request) { const { messages } = await req.json(); const result = streamText({ model: cencori('gemini-2.5-flash'), messages }); return result.toDataStreamResponse(); }

Cencori built-in security features

Cencori includes automatic PII detection, prompt injection protection, and harmful content filtering. Requests that violate safety policies are blocked before reaching the model.

Cencori multi-provider routing

Cencori supports switching between 15+ AI providers (OpenAI, Anthropic, Google, Mistral, DeepSeek, xAI, and more) without changing code by using different model IDs in the same API.

Cencori cost tracking and audit logs

Cencori provides real-time cost tracking and analytics for every request, with detailed breakdowns by model, provider, and project. Complete audit logs are maintained with full payloads, token usage, costs, and safety scores for compliance and debugging.

Cencori provider failover

Cencori supports automatic failover to backup providers if the primary provider is unavailable.

Give your agent this brain