The AI models that power your apps.
Pick the model that fits your need — from lightweight and instant to large and thorough — and give each application its own engine.
A model for every task.
- Complete control
Each application has its own model. Change it at any time without affecting anything else — no rebuild, no downtime.
- Private by design
All models run on dedicated infrastructure. Your prompts, instructions, and outputs stay in your workspace, never used to train anything.
- No API key needed
You pick the model; the platform handles the infrastructure, routing, and billing. Nothing to provision, nothing to manage.
Available models.
These open-source models are ready to use. Each one is pre-loaded, tested, and available from your app settings — just select and go.
Llama 3.1 8B
Meta — Fast · General purpose
A balanced 8-billion-parameter model for everyday tasks — chat, summarisation, and question answering. Fast responses with solid quality.
Llama 3.1 70B
Meta — Powerful · Deep reasoning
The 70-billion-parameter flagship for complex analysis, long documents, and nuanced writing. Strong reasoning and instruction following.
Mistral 7B
Mistral AI — Efficient · Low latency
A 7-billion-parameter model optimised for speed and efficiency. Excellent for high-throughput applications and quick-response assistants.
Mistral Nemo 12B
Mistral AI — Balanced · Multilingual
A 12-billion-parameter multilingual model trained jointly with NVIDIA. Better accuracy and longer context than Mistral 7B, still fast.
Gemma 2 9B
Google — Compact · High quality
Google's compact 9-billion-parameter model, punching above its weight on reasoning and instruction following thanks to knowledge distillation.
Phi-3.5 Mini
Microsoft — Ultra-light · Instant
Microsoft's 3.8-billion-parameter small language model — remarkable reasoning for its size. Ideal for fast, lightweight assistants.
Ready to build with the model of your choice?
Start free. Pick any model, write your instructions, and your app is ready in minutes.