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

# Groq

> Learn how to configure and use Groq's lightning-fast inference with Cline. Access models from OpenAI, Meta, DeepSeek, and more on Groq's purpose-built LPU architecture.

Groq provides ultra-fast AI inference through their custom LPU™ (Language Processing Unit) architecture, purpose-built for inference rather than adapted from training hardware. Groq hosts open-source models from various providers including OpenAI, Meta, DeepSeek, Moonshot AI, and others.

**Website:** [https://groq.com/](https://groq.com/)

### Getting an API Key

1. **Sign Up/Sign In:** Go to [Groq](https://groq.com/) and create an account or sign in.
2. **Navigate to Console:** Go to the [Groq Console](https://console.groq.com/) to access your dashboard.
3. **Create a Key:** Navigate to the API Keys section and create a new API key. Give your key a descriptive name (e.g., "Cline").
4. **Copy the Key:** Copy the API key immediately. You will not be able to see it again. Store it securely.

### Supported Models

Cline supports the following Groq models:

#### Featured Models

* `moonshotai/kimi-k2-instruct-0905` (Default) - Kimi K2 September update with 262K context and prompt caching ($0.60/$2.50 per 1M tokens)
* `moonshotai/kimi-k2-instruct` - Kimi K2 1T parameter model with prompt caching ($1.00/$3.00 per 1M tokens)
* `openai/gpt-oss-120b` - OpenAI's 120B open-weight MoE model ($0.15/$0.75 per 1M tokens)
* `openai/gpt-oss-20b` - OpenAI's compact 20B open-weight model ($0.10/$0.50 per 1M tokens)

#### Compound Models

* `compound-beta` - Hybrid architecture using Llama 4 Scout + Llama 3.3 70B for routing and tool use (free)
* `compound-beta-mini` - Lightweight compound model for faster inference (free)

#### Meta Llama Models

* `meta-llama/llama-4-maverick-17b-128e-instruct` - Llama 4 Maverick with 128 experts and vision support ($0.20/$0.60 per 1M tokens)
* `meta-llama/llama-4-scout-17b-16e-instruct` - Llama 4 Scout with 16 experts and vision support ($0.11/$0.34 per 1M tokens)
* `llama-3.3-70b-versatile` - Balanced performance with 131K context ($0.59/$0.79 per 1M tokens)
* `llama-3.1-8b-instant` - Fast inference with 131K context ($0.05/$0.08 per 1M tokens)

#### Reasoning Models

* `deepseek-r1-distill-llama-70b` - DeepSeek R1 reasoning distilled into Llama 70B ($0.75/$0.99 per 1M tokens)

### Configuration in Cline

1. **Open Cline Settings:** Click the settings icon (⚙️) in the Cline panel.
2. **Select Provider:** Choose "Groq" from the "API Provider" dropdown.
3. **Enter API Key:** Paste your Groq API key into the "Groq API Key" field.
4. **Select Model:** Choose your desired model from the "Model" dropdown.

### Groq's Speed Revolution

Groq's LPU architecture delivers several key advantages over traditional GPU-based inference:

#### LPU Architecture

Unlike GPUs that are adapted from training workloads, Groq's LPU is purpose-built for inference. This eliminates architectural bottlenecks that create latency in traditional systems.

#### Unmatched Speed

* **Sub-millisecond latency** that stays consistent across traffic, regions, and workloads
* **Static scheduling** with pre-computed execution graphs eliminates runtime coordination delays
* **Tensor parallelism** optimized for low-latency single responses rather than high-throughput batching

#### Quality Without Tradeoffs

* **TruePoint numerics** reduce precision only in areas that don't affect accuracy
* **100-bit intermediate accumulation** ensures lossless computation
* **Strategic precision control** maintains quality while achieving 2-4× speedup over BF16

#### Memory Architecture

* **SRAM as primary storage** (not cache) with hundreds of megabytes on-chip
* **Eliminates DRAM/HBM latency** that plagues traditional accelerators
* **Enables true tensor parallelism** by splitting layers across multiple chips

Learn more about Groq's technology in their [LPU architecture blog post](https://groq.com/blog/inside-the-lpu-deconstructing-groq-speed).

### Special Features

#### Prompt Caching

The Kimi K2 model supports prompt caching, which can significantly reduce costs and latency for repeated prompts.

#### Vision Support

Select models support image inputs and vision capabilities. Check the model details in the Groq Console for specific capabilities.

#### Reasoning Models

Some models like DeepSeek variants offer enhanced reasoning capabilities with step-by-step thought processes.

### Tips and Notes

* **Model Selection:** Choose models based on your specific use case and performance requirements.
* **Speed Advantage:** Groq excels at single-request latency rather than high-throughput batch processing.
* **OSS Model Provider:** Groq hosts open-source models from multiple providers (OpenAI, Meta, DeepSeek, etc.) on their fast infrastructure.
* **Context Windows:** Most models offer large context windows (up to 131K tokens) for including substantial code and context.
* **Pricing:** Groq offers competitive pricing with their speed advantages. Check the [Groq Pricing](https://groq.com/pricing) page for current rates.
* **Rate Limits:** Groq has generous rate limits, but check their documentation for current limits based on your usage tier.