Account & AI Modes

TensorPM separates account/sync capabilities from AI provider configuration.

Account tiers

Free

  • local workspaces
  • BYOK and local AI possible
  • cloud sync only via shared-workspace seat access

Cloud

  • cloud workspaces and sync
  • shared workspace collaboration
  • AI via BYOK or local AI

Pro

  • everything in Cloud
  • included TensorPM AI usage (Pro Model)

AI operation modes

No AI

Use TensorPM locally without any provider.

BYOK (Bring Your Own Key)

Connect your own keys for:

  • OpenAI
  • Anthropic
  • Google
  • Mistral

TensorPM provider (logged in)

When logged in, the model selector can show:

  • Lite Model
  • Pro Model (for Pro entitlements)

Local AI

TensorPM can connect to local servers, including:

  • Ollama
  • LM Studio
  • vLLM
  • custom endpoint

Model availability rules in UI

The selector only lists models that are currently usable:

  • TensorPM provider appears only when logged in
  • BYOK provider models appear only after successful key validation
  • Local AI appears only when local AI is enabled and a model is configured

If no provider is usable, the selector stays in AI fallback mode and shows setup guidance.

Current model catalog in codebase

Provider model mappings currently include:

  • OpenAI: GPT-5.2, GPT-5 Mini
  • Anthropic: Claude Opus 4.6, Claude Sonnet 4.6, Claude Opus 4.5, Claude Haiku 4.5
  • Google: Gemini 3 Pro (Preview), Gemini 3 Flash (Preview), Gemini 2.5 Flash Lite
  • Mistral: Mistral Large 3, Mistral Medium, Mistral Small

Depending on UI context, model selectors may prioritize primary models.

Where to configure

Open Settings:

  • AI tab for provider/model/keys/local AI
  • User tab for login, subscription, workspace management

Key security

BYOK keys are stored locally. Optional local encryption can be toggled when secure storage is available.

Extra integrations in AI settings

The AI settings area also includes:

  • provider rate-limit tuning
  • GitHub Copilot sub-agent toggle (when available)

Next steps