> ## Documentation Index
> Fetch the complete documentation index at: https://www.adaline.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Groq

> Integrate Groq LPU models through the Adaline Proxy for automatic telemetry and observability.

# Groq

Integrate Groq models through the Adaline Proxy to automatically capture telemetry — requests, responses, token usage, latency, and costs — with minimal code changes. Groq uses an OpenAI-compatible API.

## Supported Models

**Chat Models**

| Model | Description |
| - | - |
| `openai/gpt-oss-120b` | OpenAI GPT OSS 120B on Groq LPU |
| `openai/gpt-oss-20b` | OpenAI GPT OSS 20B on Groq LPU |
| `openai/gpt-oss-safeguard-20b` | OpenAI GPT OSS Safeguard 20B on Groq LPU |
| `moonshotai/kimi-k2-instruct` | Moonshot Kimi K2 |
| `moonshotai/kimi-k2-instruct-0905` | Moonshot Kimi K2 September 2025 snapshot |
| `meta-llama/llama-4-maverick-17b-128e-instruct` | Llama 4 Maverick |
| `meta-llama/llama-4-scout-17b-16e-instruct` | Llama 4 Scout |
| `meta-llama/llama-guard-4-12b` | Llama Guard 4 (safety) |
| `qwen/qwen3-32b` | Qwen 3 32B |
| `deepseek-r1-distill-llama-70b` | DeepSeek R1 Distill 70B |
| `llama-3.3-70b-versatile` | Llama 3.3 70B |
| `llama-3.1-8b-instant` | Llama 3.1 8B, ultra-fast inference |
| `gemma2-9b-it` | Google Gemma 2 9B |

## Proxy Base URL

```
https://gateway.adaline.ai/v1/groq/
```

## Prerequisites

1. A [Groq API key](https://console.groq.com/keys)
2. An [Adaline API key](https://www.adaline.ai/docs/admin/create-api-keys.md), project ID, and prompt ID

## Chat Completions

### Complete Chat

```python Python theme={null}
from groq import Groq

client = Groq(
    api_key="your-groq-api-key",
    base_url="https://gateway.adaline.ai/v1/groq/"
)

headers = {
    "adaline-api-key": "your-adaline-api-key",
    "adaline-project-id": "your-project-id",
    "adaline-prompt-id": "your-prompt-id"
}

response = client.chat.completions.create(
    model="llama3-8b-8192",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "What is the speed of light?"}
    ],
    extra_headers=headers
)

print(response.choices[0].message.content)
```

```typescript TypeScript theme={null}
import OpenAI from "openai";

// Groq is OpenAI-compatible
const client = new OpenAI({
  apiKey: "your-groq-api-key",
  baseURL: "https://gateway.adaline.ai/v1/groq/",
});

const response = await client.chat.completions.create(
  {
    model: "llama3-8b-8192",
    messages: [
      { role: "system", content: "You are a helpful assistant." },
      { role: "user", content: "What is the speed of light?" },
    ],
  },
  {
    headers: {
      "adaline-api-key": "your-adaline-api-key",
      "adaline-project-id": "your-project-id",
      "adaline-prompt-id": "your-prompt-id",
    },
  }
);

console.log(response.choices[0].message.content);
```

### Stream Chat

```python Python theme={null}
from groq import Groq

client = Groq(
    api_key="your-groq-api-key",
    base_url="https://gateway.adaline.ai/v1/groq/"
)

headers = {
    "adaline-api-key": "your-adaline-api-key",
    "adaline-project-id": "your-project-id",
    "adaline-prompt-id": "your-prompt-id"
}

stream = client.chat.completions.create(
    model="llama3-8b-8192",
    messages=[
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": "Explain how neural networks work."}
    ],
    stream=True,
    extra_headers=headers
)

for chunk in stream:
    if chunk.choices[0].delta.content is not None:
        print(chunk.choices[0].delta.content, end="")
```

## Next Steps

* [Multi-Step Workflows](https://www.adaline.ai/docs/integrations/examples/multi-step-workflows.md) — RAG pipelines, multi-step generation, and conversational agents
* [Headers Reference](https://www.adaline.ai/docs/reference/proxy/headers.md) — Complete header documentation

***

> [card] [Back to Integrations](https://www.adaline.ai/docs/integrations/introduction.md)
>
> Browse all integrations


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.