update blog

Author: SBrandeis

inference-providers-featherless-groq.md

@@ -23,16 +23,21 @@ authors:
 
 # Groq & Featherless AI on Hugging Face Inference Providers 🔥
 
-We're thrilled to share that **Featherless AI** is now a supported Inference Provider on the Hugging Face Hub!
-Featherless AI joins our growing ecosystem, enhancing the breadth and capabilities of serverless inference directly on the Hub’s model pages. Inference Providers are also seamlessly integrated into our client SDKs (for both JS and Python), making it super easy to use a wide variety of models with your preferred providers.
+We're thrilled to share that **Featherless AI** and **Groq** are now supported Inference Providers on the Hugging Face Hub!
+Featherless AI  and Groq join our growing ecosystem, enhancing the breadth and capabilities of serverless inference directly on the Hub’s model pages. Inference Providers are also seamlessly integrated into our client SDKs (for both JS and Python), making it super easy to use a wide variety of models with your preferred providers.
 
 [Featherless AI](https://featherless.ai) supports a wide variety of text and conversational models, including the latest open-source models from DeepSeek, Meta, Google, Qwen, and much more.
 
 Featherless AI is a serverless AI inference provider with unique model loading and GPU orchestration abilities that makes an exceptionally large catalog of models available for users. Providers often offer either a low cost of access to a limited set of models, or an unlimited range of models with users managing servers and the associated costs of operation. Featherless provides the best of both worlds offering unmatched model range and variety but with serverless pricing. Find the full list of supported models on the [models page](https://huggingface.co/models?inference_provider=featherless-ai&sort=trending).
 
-We're quite excited to see what you'll build with this new provider!
+[Groq](https://groq.com) offers a fast Inference API, powered by the LPU (Language Processing Unit), their own AI hardware processor that meets the demand for instant speed, scalability, and low latency. By optimizing compute density, memory bandwidth, and scalability, LPUs overcome performance bottlenecks and deliver ultra-low latency inference, unlocking a new class of use cases. 
+
+Take advantage of Groq for fast AI inference performance for leading openly-available models from providers like Meta, DeepSeek, Qwen, Mistral, Google, OpenAI, and more. 
+
+We're quite excited to see what you'll build with those new providers!
 
 Read more about how to use Featherless as Inference Provider in its dedicated [documentation page](https://huggingface.co/docs/inference-providers/providers/featherless-ai).
+Read more about how to use Groq as Inference Provider in its dedicated [documentation page](https://huggingface.co/docs/inference-providers/providers/groq).
 
  ## How it works
 
@@ -92,20 +97,22 @@ print(completion.choices[0].message)
 
 #### from JS using @huggingface/inference
 
+The following example shows how to use Qwen QWQ-32B using Groq as the inference provider. You can use a [Hugging Face token](https://huggingface.co/settings/tokens) for automatic routing through Hugging Face, or your own Groq cloud API key if you have one.
+
 ```js
 import { HfInference } from "@huggingface/inference";
 
 const client = new HfInference("xxxxxxxxxxxxxxxxxxxxxxxx");
 
 const chatCompletion = await client.chatCompletion({
-	model: "deepseek-ai/DeepSeek-R1-0528",
+	model: "Qwen/QwQ-32B",
 	messages: [
 		{
 			role: "user",
 			content: "What is the capital of France?"
 		}
 	],
-	provider: "featherless-ai",
+	provider: "groq",
 });
 
 console.log(chatCompletion.choices[0].message);