|
|
--- |
|
|
title: README |
|
|
emoji: 🚀 |
|
|
colorFrom: indigo |
|
|
colorTo: purple |
|
|
sdk: static |
|
|
pinned: false |
|
|
tags: |
|
|
- qubrid-ai |
|
|
- inference |
|
|
- llm |
|
|
- image-generation |
|
|
- speech-to-text |
|
|
- vision |
|
|
- ai-infrastructure |
|
|
- gpu-cloud |
|
|
- edge-ai |
|
|
thumbnail: >- |
|
|
https://cdn-uploads.huggingface.co/production/uploads/68a362d0cf6001435507cf24/3B79ePAag2zZMB2VE7uiU.png |
|
|
short_description: 'The Full Stack Platform for ' |
|
|
--- |
|
|
<p align="left"> |
|
|
<img |
|
|
src="https://ai-platform-images.s3.us-east-1.amazonaws.com/AI-Image/The+Full+AI+Stack+-+Qubrid+AI.png" |
|
|
alt="Qubrid AI" |
|
|
width="420" |
|
|
/> |
|
|
</p> |
|
|
|
|
|
--- |
|
|
|
|
|
# <a href="https://www.qubrid.com/">Qubrid AI</a> is built **for developers, researchers, and AI teams** who want: |
|
|
- Open models |
|
|
- Transparent pricing |
|
|
- Real production performance |
|
|
- Zero infra headaches |
|
|
|
|
|
We believe AI infrastructure should be **open, fast, and accessible** - not locked behind complex setups or vendor walls. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧠 What You Can Do on Qubrid |
|
|
|
|
|
- ⚡ **High-performance inference** for Text, Vision, Image, Speech & Multimodal models |
|
|
- 🛠️ **Instant Playground** - test models in the browser |
|
|
- 🔑 **Simple APIs** - drop-in inference for production |
|
|
- ☁️ **Cloud & Edge deployments** - built for real-world workloads |
|
|
- 📈 **Usage-based pricing** with free credits to start |
|
|
|
|
|
--- |
|
|
|
|
|
## 🤗 Bring Your Own Model (From Hugging Face) |
|
|
|
|
|
Have a model on Hugging Face? **Bring it to Qubrid.** |
|
|
|
|
|
- Deploy your **own open-source or custom model** |
|
|
- Run inference without hassle |
|
|
- Scale automatically with demand |
|
|
- Use the same APIs, metrics, and monitoring |
|
|
|
|
|
From experimentation → production, seamlessly. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧩 Model Categories Supported |
|
|
|
|
|
- **LLMs & Text Models** - chat, reasoning, instruction |
|
|
- **Image Generation** - diffusion & high-speed image models |
|
|
- **Vision & Multimodal** - VLMs, OCR, document understanding |
|
|
- **Speech-to-Text** - fast, accurate transcription |
|
|
- **Embeddings & RAG utilities** |
|
|
|
|
|
--- |
|
|
|
|
|
## 🧪 Get Started in Minutes |
|
|
|
|
|
- ▶️ **Playground:** https://platform.qubrid.com/playground |
|
|
- 🔑 **API Access:** Generate keys and integrate instantly |
|
|
- 💳 **Free Credits:** $1 to explore models risk-free |
|
|
|
|
|
No setup. No waiting. Just inference. |
|
|
|
|
|
--- |
|
|
|
|
|
## 💬 Join the Community |
|
|
|
|
|
👉 **Discord:** https://discord.com/invite/Btsqxa6ZnQ |
|
|
Talk to the team, get support, share feedback, and build with other developers. |
|
|
|
|
|
--- |
|
|
|
|
|
## 🌐 Learn More |
|
|
|
|
|
- 🌐 Website: https://www.qubrid.com |
|
|
- 📚 Blog: https://www.qubrid.com/blog-news |
|
|
- 📄 Docs: https://docs.platform.qubrid.com/ |
|
|
- ✉️ Contact: https://www.qubrid.com/contact |
|
|
|
|
|
--- |
|
|
|
|
|
**Welcome to Qubrid AI.** |
