Model categories
ZeroTwo organizes models into four categories:| Category | Where to use | Examples |
|---|---|---|
| Text / chat | Any chat conversation | Claude Sonnet, GPT-4o, Gemini 2.5 Pro, Grok-4 |
| Image generation | Studio → Images | GPT-Image-1, Flux Pro, Imagen 4.0 |
| Video generation | Studio → Video | AI video models (various) |
| Audio generation | Studio → Audio | AI music and voice models (various) |
Providers
ZeroTwo aggregates models from 19 text/chat providers:OpenAI
GPT-5, GPT-4o, GPT-4.1, o3, o4-mini, and more
Anthropic
Claude Opus 4.6, Claude Sonnet 4.6, Claude Haiku 4.5, and more
Gemini 3.1 Pro, Gemini 2.5 Pro, Gemini 2.5 Flash, and more
xAI
Grok-4, Grok 4 fast, and variants
Mistral
Mistral Large, Magistral, Mistral Small, Mistral Nemo
DeepSeek
DeepSeek V3, DeepSeek Reasoner
Cohere
Command A and variants
Perplexity
Sonar Pro, Sonar, and variants
Qwen
Qwen Max, Qwen Plus, and variants
Groq
Fast inference models via Groq infrastructure
OpenRouter
Additional model access via OpenRouter
More providers
Kimi, Venice, TheSys, ZAI, Inception, ByteDance, Liquid
Plan and model access
Model access in ZeroTwo is divided into two tiers:- Standard models: No monthly cap. Available on all plans including Free. Includes GPT-5-mini, GPT-4o-mini, Gemini Flash Lite, Mistral Small, Grok 4 fast, and other efficient variants.
- Premium (rate-limited) models: Counted against your monthly quota. Includes flagship models like Claude Sonnet 4.6, GPT-5, Gemini 2.5 Pro, Grok-4, and others.
| Plan | Premium message quota |
|---|---|
| Free | 0 — standard models only |
| Pro | 555 messages/month |
| Pro 2x | 1,150 messages/month |
| Plus Ultra | Unlimited |
| Business | Unlimited |
Key guides
Model picker
How to open the picker, search, filter by provider, pin favorites, and switch models mid-chat.
Premium vs. Standard
Understand the two model tiers, monthly quotas, and what happens when quota is exceeded.
Reasoning models
When to use extended-thinking models and how thinking levels work.
Anthropic (Claude)
Claude Opus, Sonnet, and Haiku — 200k context, extended thinking.
OpenAI (GPT)
GPT-5, GPT-4o, o3, o4-mini, and the full GPT lineup.
Google (Gemini)
Gemini 2.5 and 3.1 — up to 1M token context windows.

