What AI models are supported?

Tana Outliner supports state of the art LLMs from Google, Anthropic and OpenAI. See the full list of models supported across AI chat and commands in the AI chat documentation.

Some legacy models were deprecated on Nov 21, 2025. Command nodes using these will automatically be updated to fallback models.

How fast does Tana Outliner update to latest AI models?

The team strives to make the models available as soon as possible. New AI models require fine-tuning before they can be used in the app. This involves adjusting the prompts that ask AI to deliver information in Tana Outliner format. Additionally there are many out of the box AI features that need to be tested for consistency. The turnaround for this depends on engineering capacity, usually 4-8 weeks.

New models can be made available in Ask AI and Generic AI commands much faster, so the rollout is often staggered.

Can I use my own OpenAI API key?

With a Tana Outliner paid subscription, you get AI credits that are part of the plan, along with the option to use the "Ask AI" and "Ask AI (non-streaming)" command nodes with your own OpenAI API key. With other features like AI Chat, Meeting agent and most integrated AI tools in the app, Tana Outliner AI credits are used because the models need to be fine-tuned for these features to work as expected.

Commands that can be used with your own OpenAI key:

Ask AI: Simpler command, provides streaming results. Formerly "Generic AI query"
Ask AI (non-streaming): Extensive command, provides result in one batch. Formerly "Ask AI"

When setting up the commands, set the parameter "use your own AI key" and it will utilize the saved OpenAI API key in Settings.

To set your OpenAI API key, go to Settings, then API keys, then OpenAI.

Can I use my existing AI provider subscription?

No, this is not possible. Tana Outliner AI uses a mix of AI providers, not just OpenAI, which is why paid plans have AI credits included in them which can be used towards any AI model you use. For more on that, see Tana Outliner AI.

It is possible to use OpenAI's API key on select few commands. See the question above for details.

Can I retrieve the prompt I used for AI?

Yes, use the "Open GPT log monitor" via the command line. Once open, click on one of the jobs to open it. This shows you the raw inputs and output from OpenAI, including the prompt you used.

Keyboard shortcut to invoke a set of commands

Goal: Use one keyboard shortcut to bring up a very specific set of commands.

Instructions: For this example, we're going to build one command that brings up a set of commands for a bullet journaling practice. People who practice bullet journalling (or BuJo) usually decide on a list of keys or "signifiers": bullet symbols that mean different things to the writer.

In Tana Outliner, we can assume each item in the list is a separate supertag.

Build the command:

Decide on a prefix for your commands. In this example, we'll use "Bujo:"
For each of the signifiers, create a new command called "Bujo: [signifier]"
Add the command "Add tag", and insert the supertag definition to the parameter
Create a keyboard shortcut: Run "Create keyboard shortcut" in the command line, then record the shortcut you want to use. In this case, we're using Cmd/Ctrl+Shift+P. In the parameter "Commands", write the words "Bujo:"

Testing the command:

Use the keyboard shortcut Cmd/Ctrl+Shift+P
This will insert the words "Bujo:" in the command line
Type space to bring up all the options

Single command to toggle checked/unchecked field

Goal: Build one command that toggles the state of something, like a checkbox. The key that unlocks this is the obscure "Run commands in parallel" command.

Instructions:

In the schema:

Create a checkbox field called "is visible". In the Hide field setting, choose Always

Create the toggle commands:

Create a command node for checking the is visible field:
- Name: "visibility ON"
- Add node filter: >NOT:: >is visible:: true (checked)
- Add command "Set field values". In parameter "Fields to set": >is visible:: true (checked)
Make another command node that removes the field:
- Name: "visibility OFF"
- Add node filter: >is visible:: true (checked)
- Add command "Remove fields". In parameter "Fields to remove": is visible (field definition)
Create a third command node for toggling between the two commands:
- Name: "Toggle visibility"
- Add command "Run commands in parallel"
- In the parameter "Commands to run", add references to the two commands you created earlier

Test the command: On any node, run the command "Toggle visibility". It should add the is visible field to it, checked. Running it again should remove the field.

Configure visibility of command buttons:

Create or find a node that has many command buttons you want to hide
For every command, add the node filter: >Node filter:: >is visible:: true (checked)
As you do this, the buttons should, one by one, disappear from the node

Test again by running the "Toggle visibility" command on the node. It should make the buttons appear/disappear.

Further ideas:

Bind a custom keyboard shortcut to Toggle visibility
Add the toggle command as a button for mouse-click access
Use the same thing to toggle the visibility of related content sections

Can a command move node to a field of a new node?

Yes, you can. Make a new command node, and use the command "Insert Tana Outliner Paste" with the following prompt:

- ${name} #note
  - Based on:: [[^${sys:nodeId}]]

The first line is the new node. It uses the name of the current node to inform the name of the new node by using the title expression ${name}. The supertag #note can be enough for Tana Outliner to find the right tag to use, but you can specify it more precisely by adding the ^nodeID to it. See the Tana Outliner Paste documentation for more info on this convention.

To retrieve the nodeID of a supertag, run the command "Copy link (HTML formatted)" on a supertag definition and paste the results.

The second line is the field. After the name of the field and the double-colon :: is a reference to the current node that the command is being run on, which it is able to target by retrieving the nodeID of the current node using the title expression ${sys:nodeId}.

Autofill command to enrich URL nodes

The Autofill command can generate a new node title and description based on the URL.

To set up the command:

Create a new command node
Add the "Autofill fields" command
Add and check off "Autofill title" and "Autofill description" parameters to change both
Add "Model to use" to control which model you prefer. If left empty, Tana Outliner will pick the one that returns the answer with best quality and consistency

To run the command:

Run the command on a URL node using the command line
Put this command node in the Commands section of a supertag you use for URLs. Press the button to run the command

Extract start date of range using Commands

Use the "Insert relative date" command to extract the start date from a date range.

Goal: Hide the Related content sections to dial up your focus.

Instructions:

Build the single-command toggle (see the "Single command to toggle checked/unchecked field" example above for the schema setup)
Navigate to the Related content section in the configuration:
- For supertags: Cmd/Ctrl+Shift click on the tag itself
- For nodes: run the command "Configure node"
For every related content section, run the command "Add contextual content" on the related content nodes, and add >Node filter:: >is visible:: true (checked)

Testing: Run the "Toggle visibility" command on the node. It should make the related content sections appear/disappear. Optionally, you can add the Toggle visibility command to the node as a button.

Can I generate many images at once?

You can generate max. 10 images at once in Tana Outliner.

Max context limit for image generation?

Yes. If you include nodes with a lot of content or references with a lot of nodes below, you may go over the limit and it will not be possible to start the image generation (no credits will be used in this case).

What does it cost to generate an image?

The average cost of generating an image in Tana Outliner will vary with the prompt and output generated, but for normal images it will usually be around $0.15, or around 70-100 Tana Outliner AI credits.

Max tokens for image generation input?

The max number of tokens you can send as context/instructions to generate an image is 3200. You can see how many tokens are sent by typing Cmd/Ctrl+K, then "Open AI credit monitor".

Save image from AI-generated banners

Right-click on the banner, then select "Move banner image to node". Then you can download it like you would with any image.

Use AI to connect Readwise tags to topics

The Tana Outliner API that is used to power the Readwise integration is exactly the same (and therefore has the same limitations) as the Input API. It can only write new nodes to Tana Outliner, and the API can only write a single value to new fields.

So, to get all your tags out of Readwise, we recommend a comma-separated format, and then using AI to link to the correct nodes in your graph.

Here is the prompt:

PROMPT

Look at each keyword separated by the commas:

Input:
[${rwTags}]

And try to find equivalents in this list of all keywords:
//Insert search node here that finds all keywords/topics

EXAMPLE:

Input:
[arbitrage, cities, dikw, economy]

Output:
- [[Arbitrage]]
- [[Cities]]
- [[DIKW]]
- [[Economy]]

Just print the output, nothing else.

For best results, ensure that the tags in Readwise match the topic nodes in your Tana Outliner graph as closely as possible.