Groq

Groq (note: not xAI's Grok) is a LPU hardware acceleration, ultra-low latency an inference service known for, mainly hosting open-source models such as Llama / Mixtral / Whisper, with output speeds typically several times that of ordinary cloud inference.

Get API Key

• Go to GroqCloud Register account
• API Keys → Create API Key, copy gsk_... key

Configure in Cherry Studio

• After opening Settings → Model Services, find Groq Provider to enter the details page
• API key Enter gsk_...
• API Address By default https://api.groq.com/openai/v1, no need to modify
• Click Get model list

Recommended usage

Model	Suitable scenarios
llama-3.3-70b-versatile	General chat, extremely fast
llama-3.1-8b-instant	Simple tasks, millisecond-level response
mixtral-8x7b-32768	Long context
whisper-large-v3	Speech to text

Applicable scenario

• Real-time chatbots: Groq's "near-instant response" is well suited for IM integration (paired with Channels)
• High concurrency: tokens per second are significantly higher than ordinary cloud inference
• Don't care about having the newest model: Groq mainly hosts open-source models such as Llama, and does not have closed-source models like GPT-5 / Claude-4

Distinguish Grok vs Groq

	Grok	Groq
Company	xAI (Musk)	Groq Inc.
Focuses on	Self-developed large models + internet access	LPU hardware + open-source model inference
Model	grok-4 and other self-developed	llama-3.x and other open-source

Grok (xAI) and Groq are often confused. In the Cherry Studio Provider list, they are two separate entries, so please pay attention to the distinction.

---

Get help and submit feedback

If you encounter any questions, bugs, or have suggestions for feature improvements during configuration or use, please refer to Feedback and Suggestions for the official channels provided.