Back to AI Framework Overview | All Providers

@memberjunction/ai-groq

MemberJunction AI provider for Groq's ultra-fast inference platform. Extends the OpenAI provider to work with Groq's OpenAI-compatible API, providing access to LLM inference powered by Groq's custom Language Processing Units (LPUs).

Architecture

graph TD
    A["GroqLLM
(Provider)"] -->|extends| B["OpenAILLM
(@memberjunction/ai-openai)"]
    B -->|extends| C["BaseLLM
(@memberjunction/ai)"]
    A -->|overrides base URL| D["Groq API
(api.groq.com/openai/v1)"]
    D -->|runs on| E["Groq LPU
Inference Engine"]
    C -->|registered via| F["@RegisterClass"]

    style A fill:#7c5295,stroke:#563a6b,color:#fff
    style B fill:#2d6a9f,stroke:#1a4971,color:#fff
    style C fill:#2d6a9f,stroke:#1a4971,color:#fff
    style D fill:#2d8659,stroke:#1a5c3a,color:#fff
    style E fill:#b8762f,stroke:#8a5722,color:#fff
    style F fill:#b8762f,stroke:#8a5722,color:#fff
Copy

Features

• Ultra-Fast Inference: Groq's custom LPU hardware delivers extremely low latency
• OpenAI Compatible: Inherits all features from the OpenAI provider
• Streaming: Full streaming support for real-time responses
• Thinking/Reasoning: Thinking block extraction for reasoning models
• Multiple Models: Access to Llama 4, Llama 3.3, Mixtral, Gemma, and other open models optimized for Groq

Installation

npm install @memberjunction/ai-groq
Copy

Usage

import { GroqLLM } from "@memberjunction/ai-groq";

const llm = new GroqLLM("your-groq-api-key");

const result = await llm.ChatCompletion({
    model: "llama-3.3-70b-versatile",
    messages: [
        { role: "system", content: "You are a helpful assistant." },
        { role: "user", content: "Explain neural networks." },
    ],
    temperature: 0.7,
    maxOutputTokens: 1000,
});

if (result.success) {
    console.log(result.data.choices[0].message.content);
}
Copy

Streaming

const result = await llm.ChatCompletion({
    model: "llama-3.3-70b-versatile",
    messages: [{ role: "user", content: "Write a haiku about speed." }],
    streaming: true,
    streamingCallbacks: {
        OnContent: (content) => process.stdout.write(content),
        OnComplete: () => console.log("\nDone!"),
    },
});
Copy

How It Works

GroqLLM is a thin subclass of OpenAILLM that redirects API calls to Groq's endpoint at https://api.groq.com/openai/v1. Since Groq implements an OpenAI-compatible API, all chat, streaming, and parameter handling logic is inherited from the OpenAI provider.

Supported Parameters

All parameters supported by the OpenAI provider are available, including temperature, maxOutputTokens, topP, frequencyPenalty, presencePenalty, seed, stopSequences, and responseFormat.

Additionally, assistantPrefill is supported — Groq natively supports prefilling the assistant's response to guide output format. See the Prefill & Stop Sequences Guide for details.

Class Registration

Registered as GroqLLM via @RegisterClass(BaseLLM, 'GroqLLM').

Dependencies

• @memberjunction/ai - Core AI abstractions
• @memberjunction/ai-openai - OpenAI provider (parent class)
• @memberjunction/global - Class registration