> For the complete documentation index, see [llms.txt](https://help.intangible.ai/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://help.intangible.ai/chat-agents-intangible/pick-a-model.md).

# Pick a model

Choose the AI model Intangible agents think with. This is separate from the model that renders your images and videos.

The model menu in the chat panel picks the model the agents think with: the language model that reads your request, plans the job and writes the replies. The menu offers **Auto** (the default, which uses Claude Opus 5.5), **GPT-6 Luna**, **GPT-6.1 Sol**, **Claude Sonnet 5.5**, **Claude Opus 5.5** and **GPT-6 Astra**. You can also pick it on Home, beside the microphone, before you create the project. Home and the chat panel share the choice, and it goes back to Auto when you reload the page.

![The chat panel's model menu open above its button, with Auto ticked, then GPT-6 Luna, GPT-6.1 Sol, Claude Sonnet 5.5, Claude Opus 5.5 and GPT-6 Astra](https://1179478100-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FSWrjIqlgVAblx6vHGJiM%2Fuploads%2Fgit-blob-5ce0ebf93274e33d06e0cb440f2bf6299b7aa887%2Fchat-model-menu-01.png?alt=media)

## Two different models

Intangible uses AI models in two places, and they are picked separately.

|                       | Picks                                                                 | Where                                                                                                                                      |
| --------------------- | --------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------ |
| **The agents' model** | How the agents understand and plan                                    | The model menu in the chat panel                                                                                                           |
| **Render models**     | What draws the image or video, such as Nano Banana Pro or GPT Image 2 | Visualize, [Batch visualize](https://help.intangible.ai/canvas/batch-visualize.md), the edit panel, or the agents when they render for you |

The agents' model and the render model are set separately: switching one leaves the other as it was.

## Render models the agents use

When the agents render for you, the model they use is written into the shot's settings. Unless you name one, they use the defaults: **GPT Image 2.5 Sunburst** for new shots, **Nano Banana 2.1** for image edits and **Seedream 5.5** for reference sheets. Seedream 5.5 is hosted in Singapore, so if your team's model settings rule out ByteDance or hosting outside the US and EU, reference sheets fall back to GPT Image 2.6 Sunburst, then Nano Banana 2.1, then Nano Banana 2. For a different model, name it in your message: "Render shots 01 to 03 with GPT Image 2." To check what a shot used, open it in Visualize. See [AI models](https://help.intangible.ai/visualize/ai-models.md) for render models.

If you connect your own AI to Intangible over MCP, that AI uses its own model, chosen in its own app. See [Choosing a model for your MCP agent](https://help.intangible.ai/intangible-mcp-agents/choosing-a-model.md).

Each message to the agents uses credits, and how many depends on the model you picked, not on how long the agents work. Answering a choice card continues the message it came from, so it costs nothing extra. **GPT-6 Luna** is free: with it selected, the agents can build scenes, place models, set cameras and animate without spending credits on messages. Renders and videos still cost credits, because they run on render models. The menu doesn't show the cost. If a message never reaches the agents, its credits come back. See [Credits and tokens](https://help.intangible.ai/learn-more/concepts/credits-and-tokens.md).

## Related

* [Chat with Intangible](https://help.intangible.ai/chat-agents-intangible/chat-with-intangible.md)
* [AI models](https://help.intangible.ai/visualize/ai-models.md)
* [Credits and tokens](https://help.intangible.ai/learn-more/concepts/credits-and-tokens.md)


---

# Agent Instructions
This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com.

## Querying This Documentation
If you need additional information that is not directly available in this page, you can query the documentation by asking a question.

Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:

```
GET https://help.intangible.ai/chat-agents-intangible/pick-a-model.md?ask=<question>&goal=<user_goal>
```

`ask` is the immediate question: it should be specific, self-contained, and written in natural language.
`goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `automate deployments from our CI pipeline` lets GitBook tailor the answer to that use case.

The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.
