Skip to content
llmist llmist

Providers Overview

llmist supports multiple LLM providers out of the box with automatic discovery and seamless switching.

Supported Providers

Section titled “Supported Providers”
OpenAI GPT-5, GPT-4, DALL-E, TTS
Anthropic Claude Sonnet, Haiku, Opus
Gemini Gemini Pro, Flash, Imagen

Auto-Discovery

Section titled “Auto-Discovery”

llmist automatically discovers available providers from environment variables:

Terminal window
# Set one or more API keys
export OPENAI_API_KEY=sk-...
export ANTHROPIC_API_KEY=sk-ant-...
export GEMINI_API_KEY=...
import { LLMist } from 'llmist';


// Providers are auto-discovered from environment
const client = new LLMist();


// Use any available model
const agent = client.createAgent()
  .withModel('sonnet')  // Uses Anthropic
  .ask('Hello!');

Model Shortcuts

Section titled “Model Shortcuts”

Use friendly aliases instead of full model names:

AliasFull ModelProvider
gpt5openai:gpt-5OpenAI
gpt5-miniopenai:gpt-5-miniOpenAI
sonnetanthropic:claude-sonnet-4-5Anthropic
haikuanthropic:claude-haiku-4-5Anthropic
opusanthropic:claude-opus-4-5Anthropic
flashgemini:gemini-2.5-flashGemini
progemini:gemini-3-pro-previewGemini

Explicit Provider Selection

Section titled “Explicit Provider Selection”

You can also specify the provider explicitly:

// With provider prefix
.withModel('openai:gpt-5')
.withModel('anthropic:claude-sonnet-4-5-20250929')
.withModel('gemini:gemini-2.5-flash')

Manual Provider Configuration

Section titled “Manual Provider Configuration”

For advanced use cases, configure providers manually:

import { LLMist, OpenAIChatProvider } from 'llmist';


const client = new LLMist({
  autoDiscoverProviders: false,
  adapters: [
    new OpenAIChatProvider({
      apiKey: process.env.MY_OPENAI_KEY,
      baseUrl: 'https://my-proxy.com/v1',
    }),
  ],
});

Next Steps

Section titled “Next Steps”