Models

TatsuCode lets you switch between cloud, subscription, and local models quickly.

Use:

/models

This opens the model selector with filtering and capability labels.

Provider Groups

Models are grouped by source:

• OpenAI Plus/Pro (subscription OAuth)
• GitHub Copilot (subscription OAuth)
• OpenRouter (API key)
• Local Providers (Ollama, LM Studio, custom endpoints)

Some provider routes can be temporarily limited by upstream authorization status. If one route is unavailable, use another provider (for example, Gemini via OpenRouter).

Notable Model Families

Claude Family

You can also access the full Claude Code agent (with Claude's own native tools) via Claude Agent using your Pro / Max / Team / Enterprise subscription.

OpenAI Family

Gemini Family

GitHub Copilot Route (Examples)

Depending on plan, client, and current availability, Copilot can expose mixes such as:

• GPT-5 family (including coding-focused variants)
• Claude family (including Opus/Sonnet variants)
• Gemini family (including Pro/Flash variants)
• Fast coding models (for example Grok Code Fast)

Official pricing reference (subject to change):

• Copilot Free: $0 (limited)
• Copilot Pro: $10/month or $100/year
• Copilot Pro+: $39/month or $390/year
• Copilot Business: $19/user/month
• Copilot Enterprise: varies by enterprise agreement

Official docs:

• Copilot plans
• Supported Copilot models

Model Capabilities

Context Window

The context window controls how much code and history the model can process in one turn.

• ~1M context: Excellent for wide codebase understanding
• 400K context: Great for serious multi-file coding tasks
• 200K context: Strong for most production workflows

Vision

Many flagship models support image input for:

• UI screenshot debugging
• visual regression checks
• diagram or mockup understanding

Higher input image resolution is now supported on GPT-5.5 and Claude Opus 4.7 — useful for detailed UI screenshots, dense diagrams, and high-DPI mockups.

Local-provider vision auto-detection — local models that support vision (Gemma 4, Qwen-VL, and other multimodal variants) are now detected automatically by querying the local server's metadata, with self-healing retry if the server starts after TatsuCode. No manual capability flag required.

Image Generation Models

A separate model lineup is used for image generation, configured via /image-generation:

See Images for the full workflow.

Reasoning Controls

For supported models, tune reasoning depth:

/reason-effort
/reason-display

Use higher effort for complex debugging and planning; lower effort for speed.

Choosing the Right Model

Quick Pick Guide

Cost Strategy

• Use your connected subscription routes first
• Keep OpenRouter for breadth and fallback
• Use local models for private/offline workflows
• Assign cheaper models to scout-style sub-agents via /models-taskagents — see Task Agents

OpenRouter list curation: the default OpenRouter lineup has been trimmed in v0.9.107 to remove models that didn't perform well with TatsuCode's tool-calling and streaming. The remaining defaults are the ones that actually work reliably.

Model List Management

/models-add
/models-remove

• Add only what you actively use
• Keep a “fast + deep” pair in your favorites
• Switch models by task rather than sticking to one for everything

Usage and Quota

/usage
/usage-quota

• /usage shows session token usage
• /usage-quota shows subscription/API limit information where supported

If context grows too large:

/compact

Recent builds improved auto-compaction reliability and long-session recovery.

Next Steps

• Providers — connect and manage provider access
• Settings — reasoning, temperature, and display options
• AI Capabilities — what TatsuCode can do with these models