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

requesty/capabilities

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.

Requesty structured output example

Example using Requesty with structured output: import { requesty } from '@requesty/ai-sdk'; import { generateText, Output } from 'ai'; import { z } from 'zod'; const { output } = await generateText({ model: requesty('openai/gpt-4o'), output: Output.object({ schema: z.object({ recipe: z.object({ name: z.string(), ingredients: z.array(z.string()), steps: z.array(z.string()) }) }) }), prompt: 'Generate a recipe for chocolate chip cookies.' }); console.log(output.recipe);

Requesty reasoning support capabilities

Requesty supports advanced reasoning capabilities with configurable effort levels. Supported reasoning models include OpenAI (openai/o3-mini, openai/o3), Anthropic (anthropic/claude-sonnet-4-0 and other Claude reasoning models), and Deepseek (all Deepseek reasoning models with automatic reasoning).

Requesty core capabilities and features

Requesty provides universal model access to 300+ models from multiple providers with a single API key, 99.99% uptime SLA with intelligent failover and load balancing, cost optimization with pay-as-you-go pricing and prompt caching (up to 80% cost reduction), advanced security including prompt injection detection and end-to-end encryption with GDPR compliance, real-time observability with built-in monitoring and analytics, intelligent routing with automatic failover, and reasoning support with configurable effort levels.

Requesty enterprise features

Requesty offers enterprise-grade features including 99.99% uptime SLA with advanced routing and failover mechanisms, intelligent load balancing with real-time performance-based routing, cost optimization reducing API costs by up to 40%, advanced security with prompt injection detection and encryption, real-time observability with comprehensive monitoring and analytics, geographic restrictions for regional regulation compliance, and model access control with fine-grained permissions.

Give your agent this brain