home.social

#groqcloud — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #groqcloud, aggregated by home.social.

fetched live
  1. 🛡️ Enterprise-grade security with proper authentication handling, structured responses containing tool discovery, reasoning steps, and execution results

    💰 Simple pricing model - pay only for tokens consumed by selected #GroqCloud model, bring your own #MCP server and API key with third-party fees billed directly

    🔗 Works with #ResponsesAPI (native #MCP support) and #ChatCompletions API (retrofitted). #ResponsesAPI recommended for multi-step workflows and approval controls

  2. 🚀 #Groq launches remote #MCP support in beta on #GroqCloud - connecting #AI models to external tools with zero code changes for #OpenAI users

    #MCP provides universal interface to thousands of tools, transforming isolated language models into powerful, connected systems with #GitHub, browsers, databases & more

    🔄 Drop-in compatibility means existing #OpenAI #Responses API and #MCP integrations work instantly - just change endpoint to #GroqCloud for faster execution and lower costs

    🧵 👇

  3. #Groq Introduces LLaVA V1.5 7B on #GroqCloud 🚀🖼️

    #LLaVA: Large Language and #Vision Assistant 🗣️👁️
    - Combines #OpenAI's #CLIP and #Meta's #Llama2
    - Supports #image, #audio, and #text modalities

    Key Features:
    - Visual #Question Answering 🤔
    - Caption Generation 📝
    - Optical Character Recognition 🔍
    - Multimodal #Dialogue 💬

    Available now on #GroqCloud #Developer Console for #multimodal #AI innovation 💻🔧

    groq.com/introducing-llava-v1-

  4. If you like the idea of using Assistance with writing code you might like this article

    2point0.ai/posts/continue-groq

    It describes how instead of you can use the model with Continue in (or the no telemetry version) through the blindingly fast and currently free of financial cost service.

    Apart from the utility it means you could switch directly to self hosting with in the future.

    Narrator: AI Code may be subtly or dramatically wrong.