TanStack
AI v0v0
Docs
CodeRabbit
Cloudflare
Railway
AG Grid
Netlify
OpenRouter
Clerk
SerpAPI
WorkOS
Unkey
Electric
Sentry
Prisma
CodeRabbit
Cloudflare
Railway
AG Grid
Netlify
OpenRouter
Clerk
SerpAPI
WorkOS
Unkey
Electric
Sentry
Prisma
Menu
Getting Started
Comparison
Tools
Chat & Streaming
Structured Outputs
Code Mode
Media
Advanced
Migration
API
Adapters
Community Adapters
Class References
Function References
Interface References
Type Alias References
Variable References
Adapters

Groq

The Groq adapter provides access to Groq's fast inference API, featuring the world's fastest LLM inference.

Installation

sh
npm install @tanstack/ai-groq
npm install @tanstack/ai-groq

Basic Usage

typescript
import { chat } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";

const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages: [{ role: "user", content: "Hello!" }],
});
import { chat } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";

const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages: [{ role: "user", content: "Hello!" }],
});

Basic Usage - Custom API Key

typescript
import { chat } from "@tanstack/ai";
import { createGroqText } from "@tanstack/ai-groq";

const adapter = createGroqText("llama-3.3-70b-versatile", process.env.GROQ_API_KEY!, {
  // ... your config options
});

const stream = chat({
  adapter,
  messages: [{ role: "user", content: "Hello!" }],
});
import { chat } from "@tanstack/ai";
import { createGroqText } from "@tanstack/ai-groq";

const adapter = createGroqText("llama-3.3-70b-versatile", process.env.GROQ_API_KEY!, {
  // ... your config options
});

const stream = chat({
  adapter,
  messages: [{ role: "user", content: "Hello!" }],
});

Configuration

typescript
import { createGroqText, type GroqTextConfig } from "@tanstack/ai-groq";

const config: Omit<GroqTextConfig, 'apiKey'> = {
  baseURL: "https://api.groq.com/openai/v1", // Optional, for custom endpoints
};

const adapter = createGroqText("llama-3.3-70b-versatile", process.env.GROQ_API_KEY!, config);
import { createGroqText, type GroqTextConfig } from "@tanstack/ai-groq";

const config: Omit<GroqTextConfig, 'apiKey'> = {
  baseURL: "https://api.groq.com/openai/v1", // Optional, for custom endpoints
};

const adapter = createGroqText("llama-3.3-70b-versatile", process.env.GROQ_API_KEY!, config);

Example: Chat Completion

typescript
import { chat, toServerSentEventsResponse } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";

export async function POST(request: Request) {
  const { messages } = await request.json();

  const stream = chat({
    adapter: groqText("llama-3.3-70b-versatile"),
    messages,
  });

  return toServerSentEventsResponse(stream);
}
import { chat, toServerSentEventsResponse } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";

export async function POST(request: Request) {
  const { messages } = await request.json();

  const stream = chat({
    adapter: groqText("llama-3.3-70b-versatile"),
    messages,
  });

  return toServerSentEventsResponse(stream);
}

Example: With Tools

typescript
import { chat, toolDefinition } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";
import { z } from "zod";

const searchDatabaseDef = toolDefinition({
  name: "search_database",
  description: "Search the database",
  inputSchema: z.object({
    query: z.string(),
  }),
});

const searchDatabase = searchDatabaseDef.server(async ({ query }) => {
  // Search database
  return { results: [] };
});

const messages = [{ role: "user", content: "Search for something" }];

const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages,
  tools: [searchDatabase],
});
import { chat, toolDefinition } from "@tanstack/ai";
import { groqText } from "@tanstack/ai-groq";
import { z } from "zod";

const searchDatabaseDef = toolDefinition({
  name: "search_database",
  description: "Search the database",
  inputSchema: z.object({
    query: z.string(),
  }),
});

const searchDatabase = searchDatabaseDef.server(async ({ query }) => {
  // Search database
  return { results: [] };
});

const messages = [{ role: "user", content: "Search for something" }];

const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages,
  tools: [searchDatabase],
});

Model Options

Groq supports various provider-specific options:

typescript
const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages: [{ role: "user", content: "Hello!" }],
  modelOptions: {
    temperature: 0.7,
    max_completion_tokens: 1024,
    top_p: 0.9,
  },
});
const stream = chat({
  adapter: groqText("llama-3.3-70b-versatile"),
  messages: [{ role: "user", content: "Hello!" }],
  modelOptions: {
    temperature: 0.7,
    max_completion_tokens: 1024,
    top_p: 0.9,
  },
});

Reasoning

Enable reasoning for models that support it (e.g., openai/gpt-oss-120b, qwen/qwen3-32b). This allows the model to show its reasoning process, which is streamed as thinking chunks:

typescript
modelOptions: {
  reasoning_effort: "medium", // "none" | "default" | "low" | "medium" | "high"
}
modelOptions: {
  reasoning_effort: "medium", // "none" | "default" | "low" | "medium" | "high"
}

Supported Models

Groq offers a diverse selection of models from multiple providers:

Meta Llama

  • llama-3.3-70b-versatile - Fast, capable model with 128K context
  • llama-3.1-8b-instant - Fast, cost-effective model
  • meta-llama/llama-4-maverick-17b-128e-instruct - Latest Llama 4 with vision support
  • meta-llama/llama-4-scout-17b-16e-instruct - Efficient Llama 4 model

Security Models

  • meta-llama/llama-guard-4-12b - Content moderation
  • meta-llama/llama-prompt-guard-2-86m - Prompt injection detection
  • meta-llama/llama-prompt-guard-2-22m - Lightweight prompt guard

OpenAI GPT-OSS Models

  • openai/gpt-oss-120b - Large OSS model with reasoning support
  • openai/gpt-oss-20b - Efficient OSS model
  • openai/gpt-oss-safeguard-20b - Safety-tuned OSS model

Other Providers

  • moonshotai/kimi-k2-instruct-0905 - Kimi K2 with 256K context
  • qwen/qwen3-32b - Qwen 3 with reasoning support

Environment Variables

Set your API key in environment variables:

sh
GROQ_API_KEY=gsk_...
GROQ_API_KEY=gsk_...

API Reference

groqText(model, config?)

Creates a Groq chat adapter using environment variables.

Parameters:

  • model - The model name (e.g., llama-3.3-70b-versatile)
  • config (optional) - Optional configuration object. Supports the same options as createGroqText except apiKey, which is auto-detected from GROQ_API_KEY environment variable. Common options:
    • baseURL - Custom base URL for API requests (optional)

Returns: A Groq chat adapter instance.

createGroqText(model, apiKey, config?)

Creates a Groq chat adapter with an explicit API key.

Parameters:

  • model - The model name (e.g., llama-3.3-70b-versatile)
  • apiKey - Your Groq API key
  • config (optional) - Optional configuration object:
    • baseURL - Custom base URL for API requests (optional)

Returns: A Groq chat adapter instance.

Limitations

  • Text-to-Speech: Groq does not currently expose a TTS adapter. Use OpenAI, Gemini, ElevenLabs, or fal for speech generation.
  • Image Generation: Groq does not support image generation. Use OpenAI, Gemini, or fal for image generation.
  • Transcription: Groq does not currently expose a transcription adapter through TanStack AI.

Next Steps

Provider Tools

Groq does not currently expose provider-specific tool factories. Define your own tools with toolDefinition() from @tanstack/ai.

See Tools for the general tool-definition flow, or Provider Tools for other providers' native-tool offerings.

Edit on GitHub
Grok (xAI)
ElevenLabs
© 2026 TanStack LLC