Skip to main content
Available on: All plans (system defaults) / Starter+ (custom models) | Role: Organization Owner | Status: Generally Available

Overview

The AI Models section lets the Organization Owner register, validate, and manage AI models from multiple providers. Once registered, models become available for assignment to teamspaces and AI Boxes across the organization.

System Default vs. Custom Models

Every organization starts with system default models provided by the platform. Organization Owners on Starter+ plans can add custom models from supported providers.
System DefaultCustom
Available on Free planYesNo
Managed byPlatformOrganization Owner
DeletableNoYes
ConfigurableNoYes
Free plan organizations have access to system default models only. Custom model registration requires a Starter plan or higher.

Supported Providers

Singularity AI supports models from the following providers:

OpenAI

GPT-5, GPT-4.1, GPT-4o

Anthropic

Claude Opus, Claude Sonnet

Azure OpenAI

Azure-deployed OpenAI models

Google AI Studio

Gemini models

AWS Bedrock

AWS-hosted models

Mistral

Mistral models
Additional providers include DeepSeek, Vertex AI, and more.

Model Capabilities

Models are tagged with capabilities that determine where they can be used:
CapabilityDescription
ConversationGeneral chat and Q&A
StreamingReal-time response streaming
VisionImage understanding and analysis
EmbeddingsDocument vectorization for RAG (separate from chat models)
Function CallingTool use and API integration
ModerationContent filtering

How Models Are Used

Once registered, models become available across the platform:
  1. Teamspace assignment — Admins assign models to teamspaces for chat conversations. Each teamspace can have multiple models (one per capability: chat, embeddings, vision, etc.)
  2. Connection embedding — Each data connection uses an embedding model to vectorize documents for AI search
  3. AI Box execution — Models can be selected per-box for LLM-powered workflow steps
  4. Knowledge Brain processing — Brains use models for knowledge extraction, scoring, and validation

What’s Next