Auth - PraisonAI

auth tells an Agent to bill a run against a subscription seat rather than an API key.

Quick Start

Pick a provider

import { Agent } from 'praisonai';

const agent = new Agent({
  instructions: 'You are helpful',
  auth: 'claude-code',
});
const reply = await agent.chat('Hello');

Let auth choose the model

Omit llm and auth picks the provider’s default model, so a subscription token never ships to the wrong endpoint.

Default models

When you pass auth without an llm, the agent uses the provider’s default model.

Provider	Default model
`claude-code`	`anthropic/claude-sonnet-4-5`
`qwen-cli`	`openai/qwen3-coder-plus`

How it works

The credentials are resolved once on the first turn, then every outgoing request is sent through a fetch wrapper that adds the provider’s headers. Existing headers on a request win, so you can still override one deliberately. Because a subscription seat belongs to one vendor, auth also pins the default model — falling back to API-key billing would charge the wrong account, so an unregistered provider fails at construction rather than at request time.

When it throws

import { Agent } from 'praisonai';

new Agent({ instructions: 'Hi', auth: 'not-a-provider' });
// Error: Unknown subscription provider 'not-a-provider'. Registered: (none).
//   A subscription store is a host concern: register one with
//   registerAuthProvider('not-a-provider', resolver).

Credential stores (a Claude Code keychain entry, a Codex CLI file) are host concerns and are not read by the SDK. Register your own resolver with registerAuthProvider(name, resolver) — the TypeScript counterpart to Python’s register_subscription_provider.

Leaf import for bundle-sensitive callers

resolveAuth, registerAuthProvider, listAuthProviders, resetAuthProviders, and the LLMAuth, LLMAuthResolver, and LLMAuthSource types can be imported from 'praisonai', 'praisonai/llm', or the leaf module 'praisonai/llm/auth'. All three resolve to the same names — PraisonAI PR #4874 moved the implementation into llm/auth.ts and re-exports it, so the public API is unchanged.

// Any of these work — same names, same behaviour
import { registerAuthProvider } from 'praisonai';
import { registerAuthProvider } from 'praisonai/llm';
import { registerAuthProvider } from 'praisonai/llm/auth';

Prefer import { … } from 'praisonai' in application code. The leaf path 'praisonai/llm/auth' matters only when you build a custom bundle and want auth without pulling in openai or the embedding stack — the barrel (praisonai/llm) statically imports both.

Agent

Constructor options

Model Routing

How model names resolve

​Quick Start

​Default models

​How it works

​When it throws

​Leaf import for bundle-sensitive callers

​Related

Agent

Model Routing

Quick Start

Default models

How it works

When it throws

Leaf import for bundle-sensitive callers

Related