Choose the AI model you want to run and take it to production without managing servers or GPUs. Text, image, video, audio, and more, all from one platform.
Developed in Europe. Deploy wherever you need.
CHOOSE ANDDEPLOYAI MODELS.
Without choosing the GPU, provider, or runtime.
QDivZero lets you use public models, open-weight models from Hugging Face, or private and fine-tuned models. Choose the model, and QDivZero finds the compute, prepares the environment, and deploys it automatically in just a few steps. You can deploy your models across multiple regions, including Europe. Once deployed, you can connect it to your applications through an OpenAI-compatible API.
curl -X POST https://api.qdiv0.com/v1/images/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{"model":"qwen/qwen-image-2512",
"prompt":"A glowing cosmic nebula",
"size":"1024x1024",
"num_inference_steps":20,
"guidance_scale":3.5}'
A glowing cosmic nebula
qwen/qwen-image-2512
Google / gemma-4-31B-it
Vision + text, Gemma4, Base_model:Google/Gemma 4 31B model available through Hugging Face.
Qwen / Qwen3.8-27B
Vision + text, Qwen3_5, Eval Results model available through Hugging Face.
Zai Org / GLM-5.3-Flash
Vision + text, Glm5_next, En model available through Hugging Face.
Meta Llama / Llama-3.1-8B-Instruct
Text generation, Llama, Facebook model available through Hugging Face.
Prism Ml / Ternary-Bonsai-2-27B-gguf
Text generation, Llama.Cpp, Gguf model available through Hugging Face.
ISTA DASLab / Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Vision + text, Gguf, Gsq model available through Hugging Face.
JonathanColetti / Qwen3.8-27B-Uncensored-GGUF
Text generation, Llama.Cpp, Gguf model available through Hugging Face.
HauhauCS / Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Vision + text, Gguf, Uncensored model available through Hugging Face.
Google / gemma-4-31B-it
Vision + text, Gemma4, Base_model:Google/Gemma 4 31B model available through Hugging Face.
Qwen / Qwen3.8-27B
Vision + text, Qwen3_5, Eval Results model available through Hugging Face.
Zai Org / GLM-5.3-Flash
Vision + text, Glm5_next, En model available through Hugging Face.
Meta Llama / Llama-3.1-8B-Instruct
Text generation, Llama, Facebook model available through Hugging Face.
Prism Ml / Ternary-Bonsai-2-27B-gguf
Text generation, Llama.Cpp, Gguf model available through Hugging Face.
ISTA DASLab / Qwen3.8-Flash-Next-GSQ-RCO-GGUF
Vision + text, Gguf, Gsq model available through Hugging Face.
JonathanColetti / Qwen3.8-27B-Uncensored-GGUF
Text generation, Llama.Cpp, Gguf model available through Hugging Face.
HauhauCS / Qwen3.8-27B-Uncensored-HauhauCS-Aggressive-MTP-GGUF
Vision + text, Gguf, Uncensored model available through Hugging Face.
EVERYTHINGYOU NEED FOR YOURMODEL.
A model does not work alone.
An AI application needs much more than compute and inference: protecting requests, connecting your data, working with multiple models, managing fallbacks, and keeping all that logic running in production. QDivZero brings deployments, LLM Model Routing, LLM Firewall, and Retrieval together in one platform, so you can build and run your AI applications without integrating and maintaining each component separately.
One platform to run your models and everything they need around them.
Choose howYou want To pay.
One platform. Different ways to pay based on your usage.
With QDivZero, you can use balance, a subscription, or both in the same account. Balance is deducted per token for public models and by compute time for dedicated deployments. Unlimited Basic provides Qwen 3.8 27B for a fixed monthly fee without using your balance. You can activate Unlimited Basic on its own or combine it with balance to keep using other models and deployments.
The QDivZero pricing model.
Public models
01Use models that are ready for inference.
Pay for input and output tokens
- Add as much balance to your account as you need
- Tokens are deducted at each model's rate
- No fee or minimum top-up required
- Multiple providers through one API
- OpenAI-compatible API
- No user limit per account
Open-weight models
02Deploy the model on dedicated compute.
Price based on model, GPU, and capacity
- Use the same balance from your account
- Know the per-second price before deployment
- Compute prorated by the second
- Dedicated compute and private deployment
- Hugging Face or custom models
- Pay only while the deployment is active
- No user limit per account
Unlimited Basic
03Use Qwen 3.8 27B without counting tokens.
For €14.95/month
- Fixed monthly fee
- No per-token billing
- 60 requests per minute per account/API key
- 5 concurrent requests
- Activate it without balance or combine it with balance
- OpenAI-compatible API
- No user limit per account