> ## Documentation Index
> Fetch the complete documentation index at: https://docs.zerotwo.ai/llms.txt
> Use this file to discover all available pages before exploring further.
# Models
> Choose from 100+ chat, image, video, and audio models across OpenAI, Anthropic, Google, xAI, Qwen, and more in ZeroTwo.
ZeroTwo aggregates **100+ models from 20 providers** in one picker. Switch mid-conversation, filter by provider, pin favorites, and use the same credits across chat and Studio — without juggling separate API keys for every lab.
## Choose a model
Use the model control beneath the composer on [desktop](/app), [web](/web), or [mobile](/mobile). Search by name, filter by provider, or pin models you use often.
Higher reasoning effort can improve results for complex tasks, but it takes longer and uses more credits. Start with the default, then increase when the task needs deeper planning or analysis.
**Ultra** uses [subagents](/agent-configuration/subagents) to split larger work across parallel agents. Most tasks do not need Ultra.
## Recommended starting points
| Model | Provider | When to use it |
| ---------------------------------- | --------- | -------------------------------------------------------------- |
| **GPT 5.6 Sol** | OpenAI | Hardest coding, research, computer use, and high-stakes work |
| **GPT 5.6 Terra** | OpenAI | Everyday workhorse — strong reasoning at a lower cost than Sol |
| **GPT 5.6 Luna** | OpenAI | Fast, clear, repeatable tasks and high-volume runs |
| **Claude Sonnet 5** / **Opus 4.6** | Anthropic | Long context, careful writing, and complex agentic coding |
| **Gemini 3.1 Pro** / **3.5 Flash** | Google | Multimodal work and large-context analysis |
| **Grok 4.3** / **Grok 4.5** | xAI | Fast frontier chat, coding, and current-events style work |
| **Qwen 3.7 Plus** / **Max** | Qwen | Strong open-weight family for coding and general chat |
| **Kimi K3** / **K2.7 Code** | Kimi | Long-context coding and agent-style tool use |
| **DeepSeek V4 Pro** | DeepSeek | Capable reasoning at efficient cost |
| **MiniMax M3** | MiniMax | Competitive coding and agent workflows |
If you are unsure, start with **Terra** or **Auto** (when available on your plan). Move to Sol, Opus, or Max reasoning when quality matters more than speed.
### Reasoning, Max, and Ultra
* **Light / Low** — quick, well-scoped tasks
* **Medium** — default balance of speed and depth
* **High / Extra High** — multi-step work with tradeoffs
* **Max** — give one model more time on the hardest single task (enable in settings if hidden)
* **Ultra** — parallel [subagents](/agent-configuration/subagents) when the work splits cleanly
## Providers
Browse by lab. Each card jumps to that provider's model list.
GPT 5.6 Sol / Terra / Luna, GPT-5.x, o3, o4-mini, Codex
Claude Opus 5, Sonnet 5, Opus 4.x, Haiku 4.5
Gemini 3.1 Pro, 3.5 Flash, 2.5 Pro / Flash / Lite
Grok 4.5, 4.3, 4.2, Build, Code Fast
Qwen 3.7 Max / Plus, Coder, character models
Kimi K3, K2.6, K2.7 Code
DeepSeek V4 Pro and Flash
GLM 5.2, 5.1, 5, 4.7, 4.6
MiniMax M3, M2.7, M2.5
Command A+, Command A, Reasoning, R7B
Sonar and Sonar Pro
Uncensored and roleplay-oriented models
Mistral Small
C1-enhanced Claude and GPT variants
Muse Spark 1.1
Mercury 2
Gemma 4 31B
MiMo V2.5 Pro and V2.5
GPT-OSS 120B and 20B
Inkling
Browse the full public catalog anytime at [zerotwo.ai/models](https://zerotwo.ai/models). Plan limits and credits are covered on [Pricing](/pricing).
## Model lists by provider
Flagship GPT family for coding, agents, multimodal chat, and reasoning.
| Model | Notes |
| ----------------------------- | ---------------------------------------------------------- |
| GPT 5.6 Sol | Strongest GPT-5.6 — complex coding, research, computer use |
| GPT 5.6 Terra | Balanced everyday frontier model |
| GPT 5.6 Luna | Fastest / lowest-cost GPT-5.6 |
| GPT 5.5 | Previous-generation frontier model |
| GPT 5.4 / 5.4 Mini / 5.4 Nano | GPT-5.4 family |
| GPT 5.3 Chat / Codex | Chat and coding-tuned 5.3 variants |
| GPT 5.2 / 5.2 Codex | Prior 5.2 chat and Codex |
| GPT 5.1 / 5.1 Codex | Prior 5.1 chat and Codex |
| GPT 5 / 5 Mini / 5 Nano | GPT-5 family |
| GPT 4.1 / 4.1 Mini / 4.1 Nano | Instruction-following and tool use |
| GPT 4o / 4o Mini | Multimodal GPT-4o family |
| o3 / o4 Mini | Dedicated reasoning models |
Claude models for long context, careful writing, and agentic coding.
| Model | Notes |
| --------------------------- | ------------------------------------- |
| Claude Opus 5 | Latest Opus flagship |
| Claude Sonnet 5 | Latest Sonnet — strong default Claude |
| Claude Opus 4.8 / 4.7 / 4.6 | Opus 4.x series |
| Claude Sonnet 4.6 / 4.5 | Sonnet 4.x series |
| Claude Haiku 4.5 | Fast, efficient Claude |
Gemini models with large context windows and strong multimodal support.
| Model | Notes |
| ----------------------------------- | ---------------------- |
| Gemini 3.1 Pro | Latest Pro preview |
| Gemini 3.5 Flash | Fast Gemini 3.5 |
| Gemini 3 Flash | Gemini 3 Flash preview |
| Gemini 3.1 Flash-Lite | Lightweight Gemini 3.1 |
| Gemini 2.5 Pro / Flash / Flash Lite | Gemini 2.5 family |
Grok models for fast frontier chat, coding, and agent work.
| Model | Notes |
| --------------- | ------------------------- |
| Grok 4.5 | Latest main Grok |
| Grok 4.3 | Strong Grok coding / chat |
| Grok 4.2 | Hybrid reasoning Grok 4.2 |
| Grok 4 / 4 Fast | Grok 4 family |
| Grok 4.1 Fast | Speed-oriented Grok 4.1 |
| Grok Build 0.1 | Build-oriented Grok |
| Grok Code Fast | Fast coding Grok |
Alibaba Qwen family for general chat, coding, and character workflows.
| Model | Notes |
| --------------------------- | ----------------------------------- |
| Qwen 3.7 Max / Plus | Latest Qwen 3.7 flagships |
| Qwen 3.6 Plus / Flash | Qwen 3.6 family |
| Qwen 3.5 Plus | Prior Plus tier |
| Qwen3 Coder Plus / Flash | Coding-tuned Qwen3 |
| Qwen3 Next 80B I / T | Instruct and thinking Next variants |
| Qwen Plus / Flash Character | Character-oriented variants |
Moonshot Kimi models for long-context coding and agent workflows.
| Model | Notes |
| ---------------- | -------------------- |
| Kimi K3 | Latest Kimi flagship |
| Kimi K2.7 Code | Coding-focused Kimi |
| Kimi K2.6 / K2.5 | Prior K2 series |
| Model | Notes |
| ----------------- | ----------------- |
| DeepSeek V4 Pro | Main DeepSeek V4 |
| DeepSeek V4 Flash | Faster V4 variant |
GLM models from Z.ai.
| Model | Notes |
| ----------------------------- | ------------------- |
| GLM 5.2 / 5.1 / 5 | Latest GLM 5 series |
| GLM 4.7 / 4.7 Flash / Flash H | GLM 4.7 family |
| GLM 4.6 | Prior GLM 4.6 |
| Model | Notes |
| ------------------- | ------------------------- |
| MiniMax M3 | Latest MiniMax main model |
| MiniMax M2.7 / M2.5 | Prior M2 series |
| Model | Notes |
| ------------------------------- | --------------------------- |
| Command A+ | Latest Command A+ |
| Command A / Command A Reasoning | Command A family |
| Command R7B | Efficient Command R variant |
Search-oriented Sonar models.
| Model | Notes |
| --------- | ----------------------- |
| Sonar Pro | Higher-capability Sonar |
| Sonar | Standard Sonar |
Uncensored and roleplay-oriented hosted models.
| Model | Notes |
| -------------------------- | ------------------------------ |
| Venice 1.2 / 1.2 RP | Venice uncensored and roleplay |
| Mistral 3.1 24B | Venice-hosted Mistral |
| Gemma 4 (uncensored) | Venice-hosted Gemma |
| Qwen 3.6 Plus (uncensored) | Venice-hosted Qwen |
| Qwen3 235B T | Large thinking Qwen variant |
| Model | Notes |
| ------------- | ----------------------- |
| Mistral Small | Efficient Mistral Small |
C1-enhanced variants for richer structured UI responses.
| Model | Notes |
| ----------- | --------------------------- |
| C1/Sonnet 4 | Thesys C1 + Claude Sonnet 4 |
| C1/GPT-5 | Thesys C1 + GPT-5 |
| Model | Notes |
| -------------- | --------------- |
| Muse Spark 1.1 | Meta Muse Spark |
| Model | Notes |
| --------- | ------------------- |
| Mercury 2 | Inception Mercury 2 |
| Model | Notes |
| ----------- | ------------------ |
| Gemma 4 31B | Google Gemma 4 31B |
| Model | Notes |
| ------------- | ---------------------- |
| MiMo V2.5 Pro | Higher-capability MiMo |
| MiMo V2.5 | Standard MiMo V2.5 |
| Model | Notes |
| ------------ | -------------------- |
| GPT-OSS 120B | Large open GPT-OSS |
| GPT-OSS 20B | Smaller open GPT-OSS |
| Model | Notes |
| ------- | ------------------- |
| Inkling | Together AI Inkling |
## Studio models
Image, video, and audio models live in Studio selectors (separate from the chat picker).
GPT Image 2 / 1.5 / 1 / Mini, Imagen 4, Nano Banana, Flux, Qwen Image, Grok Imagine, Seedream, Ideogram, Z-Image Turbo
Seedance, Wan 2.6 Flash, Kling VIDEO 3.0, Grok Imagine Video
Gemini Lyria
ElevenLabs v3, Flash v2.5, and sound effects
See [Image generation](/image-generation) for image workflows. Media usage draws from the same [credit pool](/pricing) as chat.
## Bring your own subscription (desktop)
On the ZeroTwo desktop app you can connect a provider subscription or API key and pick those models alongside the ZeroTwo catalog:
| Connection | Example picker label |
| -------------- | ---------------------------------- |
| ChatGPT | ChatGPT (Your Subscription) |
| Claude | Claude (Your Subscription) |
| Grok | Grok Build (Your Subscription) |
| Qwen | Qwen (Your Subscription) |
| MiniMax | MiniMax (Your Subscription) |
| GitHub Copilot | GitHub Copilot (Your Subscription) |
| OpenRouter | OpenRouter (Your Key) |
| Kimi Code | Kimi Code (Your Key) |
Connect providers in **Settings → Desktop providers**. Subscription-backed models use your connected account instead of the ZeroTwo credit catalog path.
## Defaults and availability
* Availability depends on your [plan](/pricing). Free includes a limited set; paid plans unlock broader catalog access and monthly credits.
* Set a default model in app settings, or pin favorites in the picker.
* Work / Cowork and ZeroCode use the same catalog with work-agent capability filters — some models are chat-only.
* Exact IDs and metadata also appear on the public [Models hub](https://zerotwo.ai/models).
## Related
* [Pricing](/pricing) — plans, credits, and Auto allowance
* [Prompting](/prompting) — get better results from any model
* [Permission modes](/permission-modes) — control what agents can do
* [Image generation](/image-generation) — Studio image models
* [Models hub](https://zerotwo.ai/models) — full public catalog