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

Model	Context	Best For
Claude Opus 4.6	200K	Deep reasoning, architecture decisions
Claude Sonnet 4.5	200K	Strong day-to-day coding
Claude Haiku 4.5	200K	Fast edits and iteration

OpenAI Family

Model	Context	Best For
GPT-5.3 Codex	400K	Advanced coding and refactoring
GPT-5.3 Codex Spark	128K	Very fast coding iteration
GPT-5.2 / 5.1 Codex variants	400K	High-quality coding and reasoning

Gemini Family

Model	Context	Best For
Gemini 3 Pro	~1M	Large codebase context and long tasks
Gemini 3 Flash	~1M	Faster long-context tasks

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:

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

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

Task	Recommended Starting Point
Fast coding iterations	Claude Haiku 4.5, GPT-5.3 Codex Spark
Main coding workflow	Claude Sonnet 4.5, GPT-5.2/5.3 Codex
Very large context tasks	Gemini 3 Pro
Deepest analysis	Claude Opus 4.6, high-effort GPT-5.x Codex

Cost Strategy

Use your connected subscription routes first
Keep OpenRouter for breadth and fallback
Use local models for private/offline workflows

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