> ## Documentation Index
> Fetch the complete documentation index at: https://fal.ai/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# FAQ

> Common questions about fal Agent access, models, cost, limits, and programmatic use.

<AccordionGroup>
  <Accordion title="Which models can the agent use?">
    Every model in the fal catalog that your account can call. The catalog refreshes every few minutes. Restricted models are hidden from the agent and cannot be run by mention. See [Models and generation](/docs/documentation/agent/models-and-generation).
  </Accordion>

  <Accordion title="Can I choose the model myself?">
    Yes. Type `@` in the composer, open **Models**, and pick one. You can also pin a model on a plan card step. A pinned model is final. Without a pin, the agent chooses.
  </Accordion>

  <Accordion title="How much does a chat cost?">
    You pay for model runs at normal fal rates against your credits. Nothing else is billed. The agent's reasoning, the sandbox, web search, and video understanding are free to use for now. The spend chip next to the composer shows the running total. See [Access and pricing](/docs/documentation/agent/access-and-pricing).
  </Accordion>

  <Accordion title="How do I stop the agent from spending too much?">
    Set a safety cap in **Settings → Spending caps**. Runs above the cap ask for confirmation. Videos and audio ask by default. See [Spending caps](/docs/documentation/agent/spending-caps).
  </Accordion>

  <Accordion title="Why did the agent stop in the middle of a task?">
    A turn has a step limit of about 60 tool calls. Long tasks pause with a message. Send another message to continue. A plan checkpoint or a cost approval also pauses the run until you approve.
  </Accordion>

  <Accordion title="Can the agent edit my image without regenerating it?">
    Yes. Pixel-exact edits such as crop, resize, brightness, background removal, and captions run as code in the [sandbox](/docs/documentation/agent/tools/sandbox). Mark the region in the [media viewer](/docs/documentation/agent/generations/media-viewer) to point at the part to change.
  </Accordion>

  <Accordion title="Where do my files go?">
    Every input and output is saved to your fal Assets library and linked to its chat. See [Assets and characters](/docs/documentation/agent/assets-and-characters) and [Retention](/docs/documentation/agent/retention).
  </Accordion>

  <Accordion title="Can my team share a project?">
    Chats can be shared with your team or organization as read-only links. See [Sharing and forking](/docs/documentation/agent/chats/sharing). Shared editable projects are not available yet.
  </Accordion>

  <Accordion title="Is there an API or SDK for fal Agent?">
    Not yet. fal Agent is available in the browser at [fal.ai/agent](https://fal.ai/agent). For programmatic generation today, use the [Model APIs](/docs/documentation/model-apis/overview), the [MCP server](/docs/documentation/setting-up/mcp), or the [genmedia CLI](/docs/documentation/setting-up/genmedia).
  </Accordion>

  <Accordion title="Does fal Agent work on mobile?">
    Yes. The site has a mobile layout, and you can install it as an app from your browser. See [Chat interface](/docs/documentation/agent/chats/interface#install-as-an-app).
  </Accordion>

  <Accordion title="What file types can I attach?">
    Images, video, audio, documents, common code and text formats, and ZIP archives for training data. See the full table in [Composer and references](/docs/documentation/agent/chats/composer#attachments).
  </Accordion>

  <Accordion title="How do I get help?">
    Use the [fal Discord](https://discord.gg/fal-ai) or contact [support](/docs/documentation/model-apis/support). Include the chat link and the request ID from the tile's details when a run fails.
  </Accordion>
</AccordionGroup>