> For the complete documentation index, see [llms.txt](https://docs.jetadmin.io/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.jetadmin.io/ai-app-builder/ai-assistant/model-selection.md). # Select an AI model Choose an AI model, switch between quick options, and compare the models available in Jet Admin. Choose an AI model for your task, or let Jet Admin choose one automatically. ## Overview The model selector includes quick choices and individual models from Anthropic, OpenAI, and Google. Start with **Automatic** if you do not have a model preference. | Option | Model | When to choose it | | ----------- | ------------------------- | --------------------------------------------------------------------------------------- | | Automatic | Selected for each request | Let Jet Admin choose the model for your request. | | Recommended | Claude 4.6 Sonnet | A starting point for everyday work, such as adding features and refining an app. | | Smartest | Claude 4.6 Opus | Try this for complex logic, multi-step changes, or a problem that needs more reasoning. | | Fastest | Gemini 3 Flash | Use this when quick responses matter, such as small edits and short iterations. | These shortcuts reflect the options in the model selector. You can also choose a specific model from the provider sections. ![Model selector showing Automatic, Recommended, Smartest, Fastest, and provider models](https://3448227606-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2F-LQ08RFAKZvFADEiXKFy%2Fuploads%2FKV6lecLuwCVAZyQachNy%2F04-models.png?alt=media) ## How to switch models 1. Open the model selector in the AI conversation. 2. Choose **Automatic**, **Recommended**, **Smartest**, or **Fastest**. To select a specific model, browse the provider sections or use **Search**. 3. Select the model, then send your next request. If you are unsure which model to choose, start with **Automatic**. For a focused change, describe the exact result you want. If the result needs improvement, clarify the request or try **Smartest**, then review the generated changes. ## Available models The following list reflects the model selector as of September 16, 2026. Check the selector for the options currently available to you. ### Anthropic | Model | Context window shown | | ----------------- | -------------------- | | Claude 4.6 Sonnet | 1M | | Claude 4.6 Opus | 1M | | Claude 4.5 Sonnet | 1M | | Claude 4.5 Opus | 200K | | Claude 4.5 Haiku | 200K | | Claude 4.1 Opus | 200K | | Claude 4 Sonnet | 1M | ### OpenAI | Model | Context window shown | | ------------- | -------------------- | | GPT-5.4 | 1M | | GPT-5.4 Mini | 400K | | GPT-5.4 Nano | 400K | | GPT-5.3 Codex | 400K | | GPT-5.2 | 400K | | GPT-5.2 Codex | 400K | | GPT-5.1 | 400K | | GPT-5 | 400K | | GPT-5 Mini | 400K | | GPT-5 Nano | 400K | | GPT-4.1 | 1M | | GPT-4.1 Mini | 1M | ### Google | Model | Context window shown | | ---------------- | -------------------- | | Gemini 3.1 Pro | 1M | | Gemini 3 Pro | 1M | | Gemini 3 Flash | 1M | | Gemini 2.5 Pro | 1M | | Gemini 2.5 Flash | 1M | ### Self-hosted models Self-hosted models are available only on the **Enterprise plan**. The **Self-hosted models** section includes **Llama**, **Mistral**, **Qwen**, and **DeepSeek**. Open a family to see its model options. ## Understanding context windows The number beside a model indicates its context window, measured in tokens: **200K** means 200,000 tokens, **400K** means 400,000, and **1M** means one million. A context window is the amount of information a model can work with in a request, including instructions and conversation content. A larger window can accommodate more context; it does not guarantee a better answer or represent a file-upload limit. Keep requests focused and provide the information needed for the task. ## Credits and usage Model choice and task complexity affect AI usage. The selector's context-window numbers are not credit prices. For your remaining allowance, check your account's usage and billing information. See [How credits work](/account/credits-and-rate-limits/how-credits-work.md) for AI building credits. Model selection here applies to app-building requests; agent model configuration is covered in the AI Agents guides. --- # 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://docs.jetadmin.io/ai-app-builder/ai-assistant/model-selection.md?ask=&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.