Multi-Provider Agents

Switch between any LLM provider — OpenAI, Anthropic, Google, and more — without changing your agent code.

Quick Start

Simple Usage

npm install praisonai

With Configuration

import { Agent } from 'praisonai';

const agent = new Agent({
  instructions: 'You are a helpful assistant.',
  llm: 'openai/gpt-4o-mini'
});

const response = await agent.chat('Hello, how are you?');
console.log(response);

Switch Providers with One Line

import { Agent } from 'praisonai';

const agent = new Agent({
  instructions: 'You are a helpful assistant.',
  llm: 'anthropic/claude-3-5-sonnet-latest'
});

const response = await agent.chat('Explain AI in one sentence');
console.log(response);

How It Works

Supported Providers

Provider	Model String	Example
OpenAI	`openai/model`	`openai/gpt-4o`, `openai/gpt-4o-mini`
Anthropic	`anthropic/model`	`anthropic/claude-3-5-sonnet-latest`
Google	`google/model`	`google/gemini-2.0-flash`
Groq	`groq/model`	`groq/llama-3.3-70b-versatile`
Mistral	`mistral/model`	`mistral/mistral-large-latest`
Cohere	`cohere/model`	`cohere/command-r-plus`
DeepSeek	`deepseek/model`	`deepseek/deepseek-chat`
xAI	`xai/model`	`xai/grok-2`

Common Patterns

Agent with Tools

import { Agent } from 'praisonai';

function getWeather(city: string): string {
  return JSON.stringify({ city, temperature: 22, condition: 'sunny' });
}

const agent = new Agent({
  instructions: 'You help users check the weather.',
  llm: 'openai/gpt-4o-mini',
  tools: [getWeather]
});

const response = await agent.chat('What is the weather in Paris?');
console.log(response);

Structured Output

outputSchema takes a JSON Schema object (not a Zod schema) and is wired to OpenAI as response_format: { type: 'json_schema', … }, constraining the model to matching JSON. OpenAI-only — other providers log a warning and skip it. See Structured Output.

import { Agent } from 'praisonai';

const agent = new Agent({
  instructions: 'Extract person information from text.',
  llm: 'openai/gpt-4o-mini',
  outputSchema: {
    type: 'object',
    properties: {
      name: { type: 'string' },
      age: { type: 'number' },
      city: { type: 'string' },
    },
    required: ['name', 'age', 'city']
  },
  outputSchemaName: 'Person'  // names the schema in the response_format payload
});

const result = await agent.chat('John is 30 years old and lives in Paris');
// '{"name":"John","age":30,"city":"Paris"}'

outputSchema is OpenAI-only. On a non-OpenAI provider the agent warns loudly and proceeds without structured output rather than silently dropping the schema. Reasoning families (gpt-5*, o1*, o3*, o4*) omit temperature automatically. See Output → Schema-constrained output.

Multi-Agent Pipeline

import { Agent } from 'praisonai';

const researcher = new Agent({
  name: 'researcher',
  instructions: 'Research topics thoroughly.',
  llm: 'anthropic/claude-3-5-sonnet-latest'
});

const writer = new Agent({
  name: 'writer',
  instructions: 'Write engaging content based on research.',
  llm: 'openai/gpt-4o'
});

const research = await researcher.chat('Research the history of AI');
const article = await writer.chat(`Write an article based on: ${research}`);
console.log(article);

Environment Variables

export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
export GOOGLE_API_KEY=AIza...
export GROQ_API_KEY=gsk_...

# Override backend resolver
export PRAISONAI_BACKEND=ai-sdk   # Force AI SDK for all providers
export PRAISONAI_BACKEND=native   # Force native providers only
export PRAISONAI_BACKEND=auto     # Auto-select (default)

Best Practices

Use the provider/model string format

Always use "provider/model" strings ("openai/gpt-4o-mini") rather than provider-specific config objects. Switching providers is a one-line change.

Install provider packages only when needed

Core PraisonAI bundles OpenAI support. For other providers install @ai-sdk/anthropic, @ai-sdk/google, etc. only when you use them.

Match model to task

For quick tasks use openai/gpt-4o-mini or google/gemini-2.0-flash. For complex reasoning use anthropic/claude-3-5-sonnet-latest or openai/gpt-4o. Mix providers across agents in multi-agent workflows.

Store API keys in environment variables

Never hard-code API keys. Use environment variables (OPENAI_API_KEY, ANTHROPIC_API_KEY, etc.). For production deployments use a secrets manager.

Providers

Full provider reference and configuration

Structured Output

Type-safe JSON responses

​Quick Start

​How It Works

​Supported Providers

​Common Patterns

​Agent with Tools

​Structured Output

​Multi-Agent Pipeline

​Environment Variables

​Best Practices

​Related

Providers

Structured Output

Quick Start

How It Works

Supported Providers

Common Patterns

Agent with Tools

Structured Output

Multi-Agent Pipeline

Environment Variables

Best Practices

Related