Automatio

Models

The AI models a chat can run on, what each can read, and how to pick one.

Every chat runs on one AI model, which reads your messages, uses the tools and writes the replies. You pick it in the model picker and can change it at any time.

Where the model picker is: the chat composer, right of the agent panel button; its menu lists every model you can choose, with a search box. The model's name shows when the composer is wide, and on a phone or in a narrow panel only an icon shows, with the name on hover.

The model picker. 1: search. 2: the sorts. 3: the filters. 4: the Intelligence and Price sliders. 5: the Thinking slider. Prices and scores are blurred because they change.
The model picker. 1: search. 2: the sorts. 3: the filters. 4: the Intelligence and Price sliders. 5: the Thinking slider. Prices and scores are blurred because they change.

Picking a model

  1. Open the model picker in the message box.
  2. Search by name, or narrow the list with the filters: Sees images, Reads files, Sees video, Makes images, Makes video, and the All providers menu for one maker.
  3. Click a model.

Your pick becomes the model of your new chats. A chat that already has messages keeps the model it was on until you change it in that chat.

The row of sorts at the top changes the order: Recommended, Smartest, Best value, Fastest, Cheapest and Newest. The Intelligence slider hides weaker models and the Price slider hides dearer ones, and Clear filters brings everything back. A model added recently carries a New badge.

A model you cannot afford at the moment is greyed out, and hovering over it says so.

How long it thinks

At the bottom of the picker, the Thinking slider sets how long the model thinks before it answers. Auto leaves it at the model's own default; a higher setting costs more and takes longer. The slider is switched off for a model that does not think.

The picker opens on these sections. They are picked from measured scores and the cost of a typical task, and they change as new models arrive.

Everyday

ModelMade byCan readContextPrice
GLM-5.3 Flash (default)Zhipu AIimages1M$
MiMo V2.6 ProXiaomiimages, video1M$$
GPT-6.1 SolOpenAIimages, files1.1M$$$
Claude Sonnet 5.5Anthropicimages, files1M$$$
Gemini 3.8 FlashGoogleimages, video, files1M$$

Frontier

ModelMade byCan readContextPrice
Gemini 4 CarbonGoogleimages, video, files1M$$$
GPT-6 AstraOpenAIimages, files1.1M$$$$
Claude Opus 5.5Anthropicimages, files1M$$$$

Maximum

ModelMade byCan readContextPrice
Claude Fable 5.2Anthropicimages, files1M$$$$

Budget

ModelMade byCan readContextPrice
GPT-6 LunaOpenAIimages, files1.1M$
DeepSeek V4 Flash 0731DeepSeektext only1M$
MiMo V2.6 FlashXiaomiimages, video1M$
Claude Haiku 5.5Anthropicimages, files1M$

"Can read" is what the model takes besides text, such as an attached image or PDF. "Context" is how much of a conversation it holds at once. "Price" compares the price per word, from $ (cheapest) to $$$$.

Every model

ModelMade byCan readContextPrice
Claude Fable 5.1Anthropicimages, files1M$$$$
Claude Fable 5.2Anthropicimages, files1M$$$$
Claude Haiku 4.5Anthropicimages, files200K$$
Claude Haiku 5.5Anthropicimages, files1M$
Claude Opus 4.5Anthropicimages, files200K$$$$
Claude Opus 4.6Anthropicimages, files1M$$$$
Claude Opus 5.5Anthropicimages, files1M$$$$
Claude Sonnet 4.5Anthropicimages, files1M$$$
Claude Sonnet 4.6Anthropicimages, files1M$$$
Claude Sonnet 5Anthropicimages, files1M$$$
Claude Sonnet 5.5Anthropicimages, files1M$$$
GPT-4.1 MiniOpenAIimages, files1M$$
GPT-4.1 NanoOpenAIimages, files1M$
GPT-5OpenAIimages, files400K$$$
GPT-5 MiniOpenAIimages, files400K$$
GPT-5 NanoOpenAIimages, files400K$
GPT-5 ProOpenAIimages, files400K$$$$
GPT-5.1 ThinkingOpenAIimages, files400K$$$
GPT-5.2OpenAIimages, files400K$$$
GPT-5.2 ProOpenAIimages, files400K$$$$
GPT-5.3 CodexOpenAIimages, files400K$$$
GPT-5.5OpenAIimages, files1M$$$$
GPT-5.5 ProOpenAIimages, files1M$$$$
GPT-5.6 LunaOpenAIimages, files1.1M$
GPT-5.6 SolOpenAIfiles1.1M$$$$
GPT-5.6 TerraOpenAIfiles1.1M$$$
GPT-6 AstraOpenAIimages, files1.1M$$$$
GPT-6 LunaOpenAIimages, files1.1M$
GPT-6 SolOpenAIimages, files1.1M$$$
GPT-6.1 SolOpenAIimages, files1.1M$$$
GPT-6.1 TerraOpenAIimages, files1.1M$$
GPT-OSS 120BOpenAItext only131K$
GPT-OSS 20BOpenAItext only131K$
Gemini 2.5 FlashGoogleimages, video, files1M$$
Gemini 2.5 ProGoogleimages, video, files1M$$$
Gemini 3 FlashGoogleimages, video, files1M$$
Gemini 3.1 Pro PreviewGoogleimages, video, files1M$$$
Gemini 3.5 FlashGoogleimages, video, files1M$$$
Gemini 3.5 Flash LiteGoogleimages, video, files1M$$
Gemini 3.6 FlashGoogleimages, video, files1M$$
Gemini 3.7 FlashGoogleimages, video, files1M$$
Gemini 3.8 FlashGoogleimages, video, files1M$$
Gemini 4 ArgonGoogleimages, video, files1M$$$
Gemini 4 CarbonGoogleimages, video, files1M$$$
Grok 4.6xAIimages500K$$$
Grok 4.7xAIimages500K$$$
Kimi K2.5Moonshotimages, video256K$$
Kimi K2.6Moonshotimages, video262K$$
Kimi K2.7 CodeMoonshotimages, video256K$$
Kimi K3Moonshotimages, video, files1M$$$
Kimi K3.1 ProMoonshotimages1M$$$
DeepSeek V3.2DeepSeektext only128K$$
DeepSeek V3.2 ThinkingDeepSeektext only128K$$
DeepSeek V4 Flash 0731DeepSeektext only1M$
DeepSeek V4 Flash Vision ExpDeepSeekimages1M$
DeepSeek V4 ProDeepSeektext only1M$$
DeepSeek V4 Pro 0813DeepSeektext only1M$$
DeepSeek V4.1 FlashDeepSeekimages1M$$
DeepSeek V4.1 Flash 1017DeepSeekimages1M$$
GLM 4.5VZhipu AIimages66K$$
GLM-4.6Zhipu AItext only200K$$
GLM-4.7Zhipu AItext only200K$$
GLM-5Zhipu AItext only203K$$
GLM-5.1Zhipu AItext only203K$$$
GLM-5.2Zhipu AItext only1M$$$
GLM-5.3Zhipu AItext only1M$$$
GLM-5.3 Flash (default)Zhipu AIimages1M$
GLM-5.3 FlashXZhipu AIimages1M$$
Llama 3.3 70BMetatext only128K$$
Muse EmberMetaimages, files1M$
Muse Spark 1.2Metaimages, files1M$$
Muse Spark 1.2 (Contributor)Metaimages, files1M$
Muse Spark 1.3Metaimages, files1M$$
Muse Spark 1.3 (Contributor)Metaimages, files1M$
Mistral Large 4Mistralimages1M$$
Qwen 3.5 FlashAlibabaimages1M$
Qwen 3.5 PlusAlibabaimages1M$$
Qwen 3.7 FlashAlibabaimages991K$
Qwen 3.7 MaxAlibabatext only991K$$$
Qwen 3.8 FlashAlibabaimages991K$
Qwen 3.8 MaxAlibabaimages262K$$$
Qwen 3.8 Max 0902Alibabaimages991K$$$
Qwen 3.8 Omni FlashAlibabaimages1M$
Qwen3.8 27BAlibabaimages, video, files262K$$
MiniMax M2Minimaxtext only205K$$
MiniMax M3Minimaximages, files512K$$
Ling 3.0 FlashInclusionAItext only256K$
Mercury 2.5Inceptiontext only260K$
Mercury 3Inceptiontext only1M$
Particle-1Particleimages1M$
MiMo V2.6 FlashXiaomiimages, video1M$
MiMo V2.6 ProXiaomiimages, video1M$$
Step 5 PreviewStepFunimages1M$$

What a model costs

Each step the agent takes is charged at the model's own price, so a long task on an expensive model costs far more than on a cheap one. How a step is charged: Plans and credits.

Pictures and video

Image and video engines are in the picker too, under Makes images and Makes video. Picking one sets the engine the agent draws with; the chat keeps a model that talks. The engines and what each can do: Images and video.

Fine tuning

In a chat with the Tools switch off, a Model Parameters button appears beside the model picker, with settings such as temperature and maximum output.