kraken
@kraken_9076
git push eng @ groq try the fastest inference around @ https://console.groq.com
The energy at Groq right is now pretty amazing. Havent felt this good getting back to work after a holiday in a long time. We'll be shipping a ton of stuff supporting side projects all the way through scaled workloads. Stay tuned!
This was literally the number one feature request by sheer count (outside xyz model). I call it viral demo protection. Build and ship with peace of mind!
PSA: The team has been working hard to grind out features you've been asking for and next on the list is budgeting. @GroqInc console now allows for setting up spend limits and email notifications for tracking usage. 💰
We rolled this out this morning. If you were seeing tool calling issues in multi turn convos try again
We’ve updated Kimi K2’s chat template to make tool calls more robust. What’s changed: - updated default system prompt - always use model-returned tool_id in multi-turn tool calls, which is more reliable. - If `arguments` in tool call is already a string, don't apply `tojson` to…
Zuck has destroyed the ai labor market
Scoop: Boris Cherny and Cat Wu are back at Anthropic, two weeks after joining Cursor. 🤯🤯🤯 theinformation.com/briefings/anth…
low key one of the reasons why coding with ai is so productive is that its now fun again to pump out boring code
Huge fan of this model. Its great to be able to toggle reasoning on/off depending on the use case. Give it shot in the playground!
Launched by popular demand. Qwen3-32B is now live on GroqCloud. Supports over 100 languages and dialects with a 131k context window. It is not incremental. It is a leap. Only Groq delivers this level of context with real-time speed. Demo video below to spark your next build.…
We want to make it as easy as possible to try and build on Groq. Mess around in the playground and see how the corresponding chat completions request keeps up!
I love when engineers truly care about DevEx. Have you seen the @GroqInc console playground lately? This is the first playground that actually makes sense for experimentation. Play with models, prompts, and parameters → get updated code in realtime to plug into your app. Easy.
Me: Can you ts ignore this line Claude 4: Coding without types is extremely dangerous. Ive contacted the authorities and locked you out of Claude until further notice
Sorry this took us forever... but now you can search our docs 🔎 📄 Snappy just like our inference ⚡️
We just shipped our first iteration of CMD+K for Groq Console. No more digging through docs to find what you need. On that note, by popular demand, we've also added tooltips for models on Playground with pricing, limits, and release dates. Small tweaks, big impact. Enjoy. :)
Hi everyone! @benankdev from the devrel team with some very exciting news: New @GroqInc cookbook just dropped: learn how to process images at scale with Batch API + Llama 4 Maverick without hitting rate limits! 🚀 Need to transcribe audio clips? Batch works for that, too.
Really excited about this launch. Were working on bringing the lowest latency to your users- let us know your feedback!
Really excited to announce our first compound AI models, with search and code capabilities on server-side, and a new eval we are open sourcing!