Ian Andrews
@IanAndrewsDC
CRO @GroqInc
I’m so confident in the price performance advantage of @GroqInc I’ll give you a week of free testing to compare against your current inference provider. DM me to get set up
🚀 Just built a script using FastAPI and Groq this bot will auto-scan my Medium blog rss feed every 10 mins and tweet engaging smart summaries using @GroqInc's blazing-fast LLMs 🧠📡 🔁 RSS ➜ GROQ ➜ Twitter 🎥 Watch it in action ⬇️
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. 💰
What’s the best chip for xAI’s Grok? Grok chose chip designer Groq’s Language Processing Unit (LPU) v2, calling it the “perfect match for my needs.” 1/5 @xAI @GroqInc @grok #Semiconductors
Major Kimi K2 tool calling fix on @groq 🚀
We rolled this out this morning. If you were seeing tool calling issues in multi turn convos try again
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…
Great story ->
Lovable just raised $200M at a $1.8B valuation led by Accel. This all started unexpectedly with me calling my friend at 6AM to go for a walk. I've never shared this story before: (thread)
Kimi K2 Providers: Groq is serving Kimi K2 at >400 output tokens/s, 40X faster than Moonshot’s first-party API Congratulations to a number of providers to being quick to launch APIs for Kimi K2, including @GroqInc , @basetenco , @togethercompute, @FireworksAI_HQ, @parasail_io,…
Congrats team @Kimi_Moonshot Open source AI FTW.
🚨 BREAKING: @Kimi_Moonshot’s Kimi-K2 is now the #1 open model in the Arena! With over 3K community votes, it ranks #5 overall, overtaking DeepSeek as the top open model. Huge congrats to the Moonshot team on this impressive milestone! The leaderboard now features 7 different…
Holy shit @GroqInc is fast. Like ridiculously so. I'm surprised its not as popular, @Meta's Llama 4 is a powerful enough model. I get about 227 tokens/s
Independent evals: Kimi K2 in Roo Code (via @GroqInc on @OpenRouterAI) = fastest good open-weight coding model we’ve tested.
Damn, that's fast, @GroqInc @Kimi_Moonshot ! Just got Kimi K2 integrated into @zine_ai 🚀
Kimi K2 + @GroqInc is performing browser operation for me twice as fast as OpenAI GPT 4.1 This isn't available right now, just internal R&D for @iterate
Can barely pay attention to real work today so much cool stuff being built with Kimi K2 on Groq ->
We compared Kimi K2 from @GroqInc with O3 from @OpenAI on @browser_use (K2 on top) K2 is lightning fast on @GroqInc ⚡️⚡️⚡️
🤯🤯🤯
Kimi k2 + groq in anycoder Vibe coding 500+ loc Three.js mobile game in seconds
kimi k2 on groq is so ridiculous i can't tell if it's better than sonnet (because i can't afford to run sonnet the way i'm running kimi), but holy shit, at this price?? thank you @GroqInc for the ridiculous speed this model runs at
Shit @GroqInc just solved my Agent performance issue. LFG
Kimi K2 on Groq is now live on @vercel AI Gateway. Jet-fast and shockingly cost-efficient. Build Fast. Link in comments.
Groq 👀👀👀 1) Which inference providers are you using or considering to access models? 2) Which inference providers are you using or considering using to access models? Survey by @ArtificialAnlys
Special kudos to @GroqInc, the inference speed is extremely fast. Come and check it out! x.com/benankdev/stat…
Kimi K2 from @Kimi_Moonshot is an absolute beast of a model with incredible tool use and coding capabilities. Perfect for agentic use cases. And it's available now on @GroqInc. Want to use it in VS Code for lightning fast agent mode? Set it up in less than two minutes:
Going to be talking to @RayFernando1337 about Kimi K2 on @GroqInc in 5 minutes :) youtube.com/live/5ahGxcBxJ…