You can use DeepSeek-R1-Distill-Llama-70b on our servers at @groqinc.bsky.social and be sure your keystrokes won't be sent to China. console.groq.com/playground?m...
GroqCloud
Experience the fastest inference in the world
console.groq.com
January 28, 2025 at 7:42 PM
You can use DeepSeek-R1-Distill-Llama-70b on our servers at @groqinc.bsky.social and be sure your keystrokes won't be sent to China. console.groq.com/playground?m...
Qwen-2.5-Coder-32B-Instruct is live on GroqCloud™ – smart and fast code assistance at your service 🫡.
Access the model here: console.groq.com/playground?m...
Instructions to add to Cursor: x.com/ozenhati/sta...
Access the model here: console.groq.com/playground?m...
Instructions to add to Cursor: x.com/ozenhati/sta...
GroqCloud
Experience the fastest inference in the world
hubs.la
February 20, 2025 at 11:35 PM
Qwen-2.5-Coder-32B-Instruct is live on GroqCloud™ – smart and fast code assistance at your service 🫡.
Access the model here: console.groq.com/playground?m...
Instructions to add to Cursor: x.com/ozenhati/sta...
Access the model here: console.groq.com/playground?m...
Instructions to add to Cursor: x.com/ozenhati/sta...
Woke up this morning to thousands of new developers on GroqCloud™ 🤝 Something tells us you're interested in our new toy 👀 Learn more about our DeepSeek launch here:
groq.com/groqcloud-ma...
groq.com/groqcloud-ma...
GroqCloud™ Makes DeepSeek R1 Distill Llama 70B Available - Groq is Fast AI Inference
DeepSeek-R1-Distill-Llama-70b, a fine-tuned version of Llama 3.3 70B using samples generated by DeepSeek-R1, is now live on GroqCloud™ for instant reasoning
groq.com
January 28, 2025 at 10:43 PM
Woke up this morning to thousands of new developers on GroqCloud™ 🤝 Something tells us you're interested in our new toy 👀 Learn more about our DeepSeek launch here:
groq.com/groqcloud-ma...
groq.com/groqcloud-ma...
Big news! Mistral AI Saba 24B is on GroqCloud! The specialized regional language model is perfect for Middle East and South Asia-based devs and enterprises building AI solutions that need fast inference.
Learn more: groq.com/mistral-saba...
Learn more: groq.com/mistral-saba...
Mistral Saba Added to GroqCloud™ Model Suite - Groq is Fast AI Inference
GroqCloud™ has added another openly-available model to our suite – Mistral Saba. Mistral Saba is Mistral AI’s first specialized regional language model,
hubs.la
February 27, 2025 at 5:04 PM
Big news! Mistral AI Saba 24B is on GroqCloud! The specialized regional language model is perfect for Middle East and South Asia-based devs and enterprises building AI solutions that need fast inference.
Learn more: groq.com/mistral-saba...
Learn more: groq.com/mistral-saba...
Our latest model drop(s) = top requests from our dev community 👀
Yep – Qwen-2.5-32b and DeepSeek-r1-distill-qwen-32b are now live on GroqCloud™!
Learn more: groq.com/groqcloud-no...
Yep – Qwen-2.5-32b and DeepSeek-r1-distill-qwen-32b are now live on GroqCloud™!
Learn more: groq.com/groqcloud-no...
GroqCloud™ Now Offers qwen-2.5-32b and deepseek-r1-distill-qwen-32b - Groq is Fast AI Inference
One of the things we love most about our community of almost one million GroqCloud™ developers is hearing what they want next – this next model drop is one of
groq.com
February 11, 2025 at 5:21 PM
Our latest model drop(s) = top requests from our dev community 👀
Yep – Qwen-2.5-32b and DeepSeek-r1-distill-qwen-32b are now live on GroqCloud™!
Learn more: groq.com/groqcloud-no...
Yep – Qwen-2.5-32b and DeepSeek-r1-distill-qwen-32b are now live on GroqCloud™!
Learn more: groq.com/groqcloud-no...
this should be alarming to Groq fans
1. it's only a 70b distill, why can't they do the full version?
2. it's not a "production"model. what's so hard about loading weights onto your ASIC?
groq.com/groqcloud-ma...
1. it's only a 70b distill, why can't they do the full version?
2. it's not a "production"model. what's so hard about loading weights onto your ASIC?
groq.com/groqcloud-ma...
GroqCloud™ Makes DeepSeek R1 Distill Llama 70B Available - Groq is Fast AI Inference
DeepSeek-R1-Distill-Llama-70b, a fine-tuned version of Llama 3.3 70B using samples generated by DeepSeek-R1, is now live on GroqCloud™ for instant reasoning
groq.com
January 31, 2025 at 5:51 PM
this should be alarming to Groq fans
1. it's only a 70b distill, why can't they do the full version?
2. it's not a "production"model. what's so hard about loading weights onto your ASIC?
groq.com/groqcloud-ma...
1. it's only a 70b distill, why can't they do the full version?
2. it's not a "production"model. what's so hard about loading weights onto your ASIC?
groq.com/groqcloud-ma...
(5/5) The new Llama-3.3-70B model launched and is now available to all 645,000 GroqCloud™ developers as of this morning. Go cook, and don't forget to share what you build here.
Thank you for making GroqCloud™ the #1 API for fast inference! This is only just the beginning.
Thank you for making GroqCloud™ the #1 API for fast inference! This is only just the beginning.
December 6, 2024 at 6:11 PM
(5/5) The new Llama-3.3-70B model launched and is now available to all 645,000 GroqCloud™ developers as of this morning. Go cook, and don't forget to share what you build here.
Thank you for making GroqCloud™ the #1 API for fast inference! This is only just the beginning.
Thank you for making GroqCloud™ the #1 API for fast inference! This is only just the beginning.
Llama 4 Scout is now available on Groq and both models are available GroqCloud.
April 5, 2025 at 7:59 PM
Llama 4 Scout is now available on Groq and both models are available GroqCloud.
Batch Processing allows users to batch together non-time sensitive requests or submit large scale workloads and get a response back within 24 hours. All paid customers get 50% off through April 2025.
For more on Batch processing documentation on GroqCloud: console.groq.com/docs/batch
For more on Batch processing documentation on GroqCloud: console.groq.com/docs/batch
GroqCloud
Experience the fastest inference in the world
hubs.la
March 14, 2025 at 4:55 AM
Batch Processing allows users to batch together non-time sensitive requests or submit large scale workloads and get a response back within 24 hours. All paid customers get 50% off through April 2025.
For more on Batch processing documentation on GroqCloud: console.groq.com/docs/batch
For more on Batch processing documentation on GroqCloud: console.groq.com/docs/batch
looks like Groq is hosting Scout & Maverick at a 4-bit quant console.groq.com/docs/models
GroqCloud - Build Fast
Build Fast with GroqCloud
console.groq.com
April 5, 2025 at 8:17 PM
looks like Groq is hosting Scout & Maverick at a 4-bit quant console.groq.com/docs/models
GroqCloud™ now has the latest from Alibaba Qwen that dropped today. Devs, try the preview yourself at console.groq.com.
March 6, 2025 at 12:24 AM
GroqCloud™ now has the latest from Alibaba Qwen that dropped today. Devs, try the preview yourself at console.groq.com.
Si vous voulez tester DeepSeek sans que vos données partent en Chine pour des raisons évidentes, vous pouvez utiliser @groq.com (bon, par contre, ça partira aux US…) console.groq.com/playground
PS : qq'un connaît un service similaire mais hébergé en Europe ?
#DeepSeek #IA #GroqCloud
PS : qq'un connaît un service similaire mais hébergé en Europe ?
#DeepSeek #IA #GroqCloud
GroqCloud
Experience the fastest inference in the world
console.groq.com
January 29, 2025 at 2:40 PM
Si vous voulez tester DeepSeek sans que vos données partent en Chine pour des raisons évidentes, vous pouvez utiliser @groq.com (bon, par contre, ça partira aux US…) console.groq.com/playground
PS : qq'un connaît un service similaire mais hébergé en Europe ?
#DeepSeek #IA #GroqCloud
PS : qq'un connaît un service similaire mais hébergé en Europe ?
#DeepSeek #IA #GroqCloud
The @groq.com + @vercel.com integration is live 🚀
Connect your Vercel projects directly to GroqCloud™ for ultra-fast AI inference. Build fast, deploy easily, and get low-latency access to state-of-the-art models.
Try it now: vercel.com/integrations...
Connect your Vercel projects directly to GroqCloud™ for ultra-fast AI inference. Build fast, deploy easily, and get low-latency access to state-of-the-art models.
Try it now: vercel.com/integrations...
Groq for Vercel – Vercel
Fast Inference for AI Applications
vercel.com
March 18, 2025 at 5:26 PM
The @groq.com + @vercel.com integration is live 🚀
Connect your Vercel projects directly to GroqCloud™ for ultra-fast AI inference. Build fast, deploy easily, and get low-latency access to state-of-the-art models.
Try it now: vercel.com/integrations...
Connect your Vercel projects directly to GroqCloud™ for ultra-fast AI inference. Build fast, deploy easily, and get low-latency access to state-of-the-art models.
Try it now: vercel.com/integrations...
Sources: bids for GroqCloud, Groq's AI inference platform, are expected to exceed $1B after Nvidia's $20B non-exclusive licensing agreement with Groq (Kate Clark/Wall Street Journal)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
December 31, 2025 at 6:36 AM
Sources: bids for GroqCloud, Groq's AI inference platform, are expected to exceed $1B after Nvidia's $20B non-exclusive licensing agreement with Groq (Kate Clark/Wall Street Journal)
Main Link | Techmeme Permalink
Main Link | Techmeme Permalink
Or run queries on Groq Playground:
console.groq.com/playground?m...
Groq is an extremely fast inference processor. You get pages and pages of responses in second. Exactly what sort of superhumans do you think are behind the curtain able to type that fast?
Just stop. It's embarrassing.
console.groq.com/playground?m...
Groq is an extremely fast inference processor. You get pages and pages of responses in second. Exactly what sort of superhumans do you think are behind the curtain able to type that fast?
Just stop. It's embarrassing.
GroqCloud
Experience the fastest inference in the world
console.groq.com
May 15, 2024 at 10:37 PM
Or run queries on Groq Playground:
console.groq.com/playground?m...
Groq is an extremely fast inference processor. You get pages and pages of responses in second. Exactly what sort of superhumans do you think are behind the curtain able to type that fast?
Just stop. It's embarrassing.
console.groq.com/playground?m...
Groq is an extremely fast inference processor. You get pages and pages of responses in second. Exactly what sort of superhumans do you think are behind the curtain able to type that fast?
Just stop. It's embarrassing.
Today we’re launching our new weekly video series 🚀
It includes GroqCloud™ feature updates, customer use cases, and developer highlights.
Tune in every Thursday to get Groq news fast by subscribing to our YouTube channel.
Watch the first episode now: youtu.be/-IaqtVYzPHY?...
It includes GroqCloud™ feature updates, customer use cases, and developer highlights.
Tune in every Thursday to get Groq news fast by subscribing to our YouTube channel.
Watch the first episode now: youtu.be/-IaqtVYzPHY?...
Groq Speed Read Newsletter (Video Edition)
YouTube video by Groq
youtu.be
January 16, 2025 at 11:24 PM
Today we’re launching our new weekly video series 🚀
It includes GroqCloud™ feature updates, customer use cases, and developer highlights.
Tune in every Thursday to get Groq news fast by subscribing to our YouTube channel.
Watch the first episode now: youtu.be/-IaqtVYzPHY?...
It includes GroqCloud™ feature updates, customer use cases, and developer highlights.
Tune in every Thursday to get Groq news fast by subscribing to our YouTube channel.
Watch the first episode now: youtu.be/-IaqtVYzPHY?...
My workaround at the moment (my problem statement was: I don't want to spend money) was to start using Groq (console.groq.com/docs/overview) with online endpoints of open source LLMs, available for free under certain rate / token limits per day.
GroqCloud
Experience the fastest inference in the world
console.groq.com
March 9, 2025 at 5:22 PM
My workaround at the moment (my problem statement was: I don't want to spend money) was to start using Groq (console.groq.com/docs/overview) with online endpoints of open source LLMs, available for free under certain rate / token limits per day.
とりあえず蒸留版は対応してきたね => GroqCloud™ Makes DeepSeek R1 Distill Llama 70B Available - Groq is Fast AI Inference
https://groq.com/groqcloud-makes-deepseek-r1-distill-llama-70b-available/
https://groq.com/groqcloud-makes-deepseek-r1-distill-llama-70b-available/
GroqCloud™ Makes DeepSeek R1 Distill Llama 70B Available - Groq is Fast AI Inference
DeepSeek-R1-Distill-Llama-70b, a fine-tuned version of Llama 3.3 70B using samples generated by DeepSeek-R1, is now live on GroqCloud™ for instant reasoning
groq.com
January 28, 2025 at 11:24 PM
とりあえず蒸留版は対応してきたね => GroqCloud™ Makes DeepSeek R1 Distill Llama 70B Available - Groq is Fast AI Inference
https://groq.com/groqcloud-makes-deepseek-r1-distill-llama-70b-available/
https://groq.com/groqcloud-makes-deepseek-r1-distill-llama-70b-available/
Groq launches its Developer Tier for GroqCloud, offering increased rate limits, batch API discounts, and Flex Tier access. Developers can build and scale AI inference effectively. Learn about the features here: https://groq.com/blog/developer-tier-now-available-on-groqcloud
July 5, 2025 at 6:00 AM
Groq launches its Developer Tier for GroqCloud, offering increased rate limits, batch API discounts, and Flex Tier access. Developers can build and scale AI inference effectively. Learn about the features here: https://groq.com/blog/developer-tier-now-available-on-groqcloud
📣 ICYMI: Dev Tier self-serve access is now live! This means pay-as-you-go, on-demand access to GroqCloud™ that can grow with you is here.
Learn more: groq.com/developer-ti...
Learn more: groq.com/developer-ti...
GroqCloud™ Developer Tier Self-serve Access Now Available - Groq is Fast AI Inference
We’re expanding access to GroqCloud™, ramping up our Developer Tier which is a self-serve access point (or upgrade if you’ve been using our Free Tier up until
groq.com
February 12, 2025 at 10:15 PM
📣 ICYMI: Dev Tier self-serve access is now live! This means pay-as-you-go, on-demand access to GroqCloud™ that can grow with you is here.
Learn more: groq.com/developer-ti...
Learn more: groq.com/developer-ti...
GroqCloud
Experience the fastest inference in the world
console.groq.com
January 28, 2025 at 10:03 PM
📢 Word level time stamping, one of the most requested features by devs, is now available on GroqCloud. 🎉
Make content more accessible, navigable & useful for end users by bridging the gap between text and audio/video with WLTS.
Try it for yourself at hubs.ly/Q03bV3G60.
Make content more accessible, navigable & useful for end users by bridging the gap between text and audio/video with WLTS.
Try it for yourself at hubs.ly/Q03bV3G60.
March 14, 2025 at 4:24 PM
📢 Word level time stamping, one of the most requested features by devs, is now available on GroqCloud. 🎉
Make content more accessible, navigable & useful for end users by bridging the gap between text and audio/video with WLTS.
Try it for yourself at hubs.ly/Q03bV3G60.
Make content more accessible, navigable & useful for end users by bridging the gap between text and audio/video with WLTS.
Try it for yourself at hubs.ly/Q03bV3G60.
Learn more about Batch Processing and what it unlocks for builders in our blog: groq.com/batch-proces...
Batch Processing with GroqCloud™ for AI Inference Workloads - Groq is Fast AI Inference
GroqCloud™ provides fast inference for complex AI solutions that require instant responsiveness. But what happens when your use cases expand and require
groq.com
March 14, 2025 at 4:55 AM
Learn more about Batch Processing and what it unlocks for builders in our blog: groq.com/batch-proces...
Thank you very much. Is it possible to use also the groq API, which is openai compatible?
console.groq.com/docs/openai
console.groq.com/docs/openai
GroqCloud
Experience the fastest inference in the world
console.groq.com
December 10, 2024 at 8:14 AM
Thank you very much. Is it possible to use also the groq API, which is openai compatible?
console.groq.com/docs/openai
console.groq.com/docs/openai