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. Every step of a workflow runs on the model of the app it calls, so a chained flow keeps the same engines you picked.

Alibaba

Qwen3

Alibaba

General-purpose model from the Qwen 3 family (Alibaba), balancing reasoning and speed.

256K Text
4B 8B

Qwen3 Embedding

Alibaba

Embedding model from the Qwen 3 family (Alibaba), built for semantic search and vectorization.

40K Text
4B 8B

Qwen3 VL

Alibaba

Vision-language model from the Qwen 3 family (Alibaba), built for image and document analysis.

256K Text Image
4B 8B

Qwen3.5

Alibaba

Latest-generation general-purpose model from the Qwen family (Alibaba), powerful and versatile.

256K Text Image
4B 9B
Google

Code Gemma

Google

Gemma variant (Google) specialized in code generation and completion.

8K Text
2B 7B

Embedding Gemma

Google

Compact Gemma-family embedding model (Google) for semantic search.

2K Text
300M

Gemma 3

Google

Open general-purpose model from the Gemma 3 family (Google), multimodal and efficient.

128K Text Image
4B 12B

Gemma 4

Google

Open general-purpose model from the Gemma 4 family (Google), multimodal and available from compact to most powerful.

128K Text Image
e4B 12B

Shield Gemma

Google

Gemma model (Google) dedicated to content moderation and safety.

8K Text
2B 9B

Translate Gemma

Google

Gemma-family model (Google) specialized in multilingual translation.

128K Text Image
4B 12B
Mistral AI

Codestral

Mistral AI

Mistral AI model specialized in code generation across many languages.

32K Text
22B

Devstral Small 2

Mistral AI

Devstral-family model (Mistral AI) specialized in software development and code generation.

384K Text Image
24B

Mathstral

Mistral AI

Mistral AI model specialized in mathematical and scientific reasoning.

32K Text
7B

Ministral 3

Mistral AI

Compact Mistral AI model designed for on-device efficiency and low latency.

256K Text Image
3B 8B 14B

Mistral

Mistral AI

General-purpose Mistral AI model known for its performance/efficiency balance.

32K Text
7B

Mistral Small 3.2

Mistral AI

Compact, fast Mistral AI model with a good quality/cost trade-off.

128K Text Image
24B
IBM

Granite 3.1 Dense

IBM

Dense model from the Granite 3.1 family (IBM), balanced for general tasks.

128K Text
2B 8B

Granite 3.1 MoE

IBM

Mixture-of-experts (MoE) Granite 3.1 model (IBM), efficient at scale.

128K Text
3B

Granite 3.2 Vision

IBM

Compact model from the Granite 3.2 family (IBM) specialized in image and document analysis.

16K Text Image
2B

Granite 3.3

IBM

General-purpose model from the Granite 3 family (IBM), built for professional use.

128K Text
2B 8B

Granite 4

IBM

Latest-generation general-purpose model from the Granite family (IBM), enterprise-oriented.

128K Text
3B

Granite 4.1

IBM

General-purpose model from the Granite 4.1 family (IBM), balanced for everyday text tasks.

128K Text
3B 8B

Granite Code

IBM

Granite-family model (IBM) specialized in code generation.

125K Text
3B 8B

Granite Guardian 4.1

IBM

Granite 4.1-family model (IBM) dedicated to content moderation and safety.

128K Text
8B
Microsoft

Phi 3.5

Microsoft

Capable small model from the Phi family (Microsoft), efficient for its size.

128K Text
3.8B

Phi 4

Microsoft

Compact model from the Phi 4 family (Microsoft), strong at reasoning for its size.

16K Text
14B

Phi 4 mini

Microsoft

Very small Phi 4 model (Microsoft), designed for speed and on-device use.

128K Text
3.8B

Phi 4 mini reasoning

Microsoft

Mini Phi 4 (Microsoft) specialized in low-cost reasoning.

128K Text
3.8B

Phi 4 reasoning

Microsoft

Phi 4 variant (Microsoft) optimized for step-by-step reasoning.

32K Text
14B
DeepSeek

DeepSeek Coder V2

DeepSeek

DeepSeek model specialized in code generation and completion.

160K Text
16B

DeepSeek OCR

DeepSeek

Compact DeepSeek-family model (DeepSeek) specialized in document reading and text recognition.

8K Text Image
3B

DeepSeek R1

DeepSeek

DeepSeek reasoning model built for complex, step-by-step problem solving.

128K Text
1.5B 8B

DeepSeek V2

DeepSeek

General-purpose mixture-of-experts model from DeepSeek, powerful and cost-efficient.

160K Text
16B
OpenBMB

MiniCPM-V 4.5

OpenBMB

Compact multimodal model from the MiniCPM-V family (OpenBMB), efficient on both text and images.

40K Text Image
8B

MiniCPM-V 4.6

OpenBMB

Very compact multimodal model from the MiniCPM-V family (OpenBMB), built for lightweight processing.

256K Text Image
1B
Liquid AI

LFM2.5

Liquid AI

General-purpose model from the LFM family (Liquid AI), compact and fast for text tasks.

125K Text
8B

Ready to build with the model of your choice?

Start free. Pick any model, write your instructions, and your app is ready in minutes.