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

# Models and effort levels

> Which models Claude Desktop on 3P offers, the default model and its starting effort level, per-model effort caps, display names, and 1M-context variants

Claude Desktop on third-party (3P) builds the model picker in Chat, Cowork, and Code from your configuration. Your configuration decides which models the picker offers, which model and effort level each new conversation starts with, and which effort levels users can choose. You control all three with the keys under **Models** in the [in-app configuration window](https://claude.com/docs/third-party/claude-desktop/in-app-configuration.md). The [configuration reference](https://claude.com/docs/third-party/claude-desktop/configuration.md#models) lists every field.

## Model list and default model

[`inferenceModels`](https://claude.com/docs/third-party/claude-desktop/configuration#inferencemodels) lists the models the picker offers. Write each entry with the exact model ID your provider expects, such as `us.anthropic.claude-sonnet-5` on Amazon Bedrock or `claude-sonnet-5` on Google Cloud's Agent Platform. The first entry is the default model. New Chat conversations, Cowork sessions, and Code sessions start on the default model until a user picks another model. To control whether a user's choice carries over to later conversations and sessions, see [Start every conversation on the default model](#start-every-conversation-on-the-default-model).

If you leave `inferenceModels` unset and your provider supports [model discovery](https://claude.com/docs/third-party/claude-desktop/configuration.md#modeldiscoveryenabled), Claude Desktop fills the picker from the provider's model list at launch. The first discovered model is then the default model.

Each entry is either a model ID string or an object. In an object, `name` holds the model ID and every other field is optional. These optional fields change how the picker shows the model:

* `labelOverride` sets the display name for an ID the picker can't turn into a readable name, such as a gateway routing alias or an Amazon Bedrock application inference profile ARN. Claude Desktop still sends `name` to your provider.
* `supports1m: true` adds a second entry that shows the same name with **1M context window** beneath it. Set it only when your deployment accepts 1M-token requests for that model. Otherwise, requests from the 1M entry fail at the provider.
* `prefer1m: true`, with `supports1m: true`, shows the model as one entry. New conversations with it use the 1M context window. To do this for every entry that sets `supports1m`, set [`modelPrefer1mContext`](https://claude.com/docs/third-party/claude-desktop/configuration#modelprefer1mcontext) to `true`. When discovery fills the picker from a gateway, that key applies to every model the gateway [marks as supporting 1M](https://claude.com/docs/third-party/claude-desktop/gateway.md#models).
* `behavesAs` names the Claude model behind an ID that Claude Desktop can't identify, such as a gateway routing alias. The picker then shows that model's **Effort** control. See [Map an unrecognized model ID to a Claude model](#map-an-unrecognized-model-id-to-a-claude-model).

On any provider, a Chat conversation, Cowork session, or Code session on an entry without `supports1m` assumes a context window from the model ID:

* **An ID recognized as a model with a native 1M context window**, such as `us.anthropic.claude-opus-5`: you don't need `supports1m` or `prefer1m`. Setting them doesn't change the assumed window. For earlier Claude Desktop versions, see [Context window and compaction](https://claude.com/docs/third-party/claude-desktop/gateway.md#context-window-and-compaction) on the LLM gateway page. To check a model, see [Extended context](https://code.claude.com/docs/en/model-config#extended-context) in the Claude Code documentation, which lists the models that run with the 1M window by default.
* **An ID for a model without a native 1M context window, or an unrecognized ID whose entry doesn't set `behavesAs`**, such as `us.anthropic.claude-opus-4-6-v1` or a gateway routing alias: the assumed window is 200K tokens. If your deployment accepts 1M-token requests for the model, [set a larger context window for it](#set-a-larger-context-window-for-a-model).
* **An unrecognized ID whose entry sets [`behavesAs`](#map-an-unrecognized-model-id-to-a-claude-model)**, through an LLM gateway: the assumed window is the window of the model that `behavesAs` names.

### Set a larger context window for a model

A session compacts a long conversation to fit the context window that it assumes for the model, even when your provider accepts more. If your deployment accepts 1M-token requests for a model that sessions assume 200K tokens for, declare that on the model's `inferenceModels` entry:

* **A gateway routing alias for a Claude model with a native 1M context window**, such as Claude Sonnet 5: set [`behavesAs`](#map-an-unrecognized-model-id-to-a-claude-model) to that model's ID. New sessions on the alias assume that model's window.
* **Any other model that your deployment serves with a 1M context window**: set `supports1m` and `prefer1m`. New Chat conversations, Cowork sessions, and Code sessions on the model request the 1M context window from your provider. With `supports1m` alone, only sessions that a user starts on the **1M context window** entry get the larger window.

The following configuration declares a larger window for two gateway routing aliases:

```json theme={null}
{
  "inferenceModels": [
    {
      "name": "acme-claude-sonnet",
      "behavesAs": "claude-sonnet-5"
    },
    {
      "name": "acme-claude-large",
      "supports1m": true,
      "prefer1m": true
    }
  ]
}
```

After users [relaunch Claude Desktop](https://claude.com/docs/third-party/claude-desktop/configuration-format.md#when-a-configuration-change-on-a-device-takes-effect) and start a new session on either alias, the session goes past 200K tokens without compacting. To confirm it in your gateway's logs, see the first requirement under [Context window and compaction](https://claude.com/docs/third-party/claude-desktop/gateway.md#context-window-and-compaction) on the LLM gateway page.

Declare a larger window only for a model that accepts the larger requests. If the model accepts less, requests past its real limit fail at your provider. Through a gateway, the session then compacts only if the gateway forwards the provider's too-long error unchanged.

## Effort levels

An effort level sets how much thinking Claude puts into each response. Higher levels give more thorough answers but take longer and use more tokens. Users choose the level with the **Effort** control in the model picker.

Each model starts at Anthropic's recommended level unless you configure otherwise. The **Effort** control marks the recommended level **Default**.

### Per-model effort cap

[`maxEffort`](https://claude.com/docs/third-party/claude-desktop/configuration#inferencemodels) on an `inferenceModels` entry sets the highest effort level Claude Desktop offers for that model in Chat, Cowork, and Code. Set it to `low`, `medium`, `high`, `xhigh`, or `max`. The picker shows `xhigh` as **Extra**. The **Effort** control doesn't offer levels above the cap.

In Code sessions, the cap also limits Claude Code's own effort settings, such as a `CLAUDE_CODE_EFFORT_LEVEL` environment variable or the `/effort` command. If a model's recommended level is above its cap, the model starts at the cap. If Claude Desktop doesn't recognize the `maxEffort` value, it caps the model at low.

### Starting effort level for the default model

[`defaultModelEffort`](https://claude.com/docs/third-party/claude-desktop/configuration#defaultmodeleffort) sets the effort level the default model starts at, in place of its recommended level. Other models keep their recommended level. If you set a level the default model doesn't offer, or one above its `maxEffort`, the default model starts at the nearest lower level it offers.

In Code, the `CLAUDE_CODE_EFFORT_LEVEL` environment variable or `effortLevel` in Claude Code's settings takes priority.

`defaultModelEffort` also applies when [model discovery](https://claude.com/docs/third-party/claude-desktop/configuration.md#modeldiscoveryenabled) fills the picker instead of an `inferenceModels` list.

### Map an unrecognized model ID to a Claude model

Some model IDs, such as a gateway routing alias, don't name a specific Claude model, so the picker shows no **Effort** control for them. To give such an ID the controls of the Claude model behind it, set [`behavesAs`](https://claude.com/docs/third-party/claude-desktop/configuration#inferencemodels) on its `inferenceModels` entry to that model's ID. In the [in-app configuration window](https://claude.com/docs/third-party/claude-desktop/in-app-configuration.md), enter that ID in the model's **Claude model behind this ID** field. Requires Claude Desktop 4.29.0 or later.

```json theme={null}
{
  "inferenceModels": [
    {
      "name": "acme-claude-sonnet",
      "behavesAs": "claude-sonnet-5"
    }
  ]
}
```

With this entry, the picker shows `acme-claude-sonnet` with the controls of Claude Sonnet 5: its effort levels in Chat, Cowork, and Code, and its **Thinking** switch in Chat and Cowork. The model starts at Claude Sonnet 5's recommended level, and `defaultModelEffort` and `maxEffort` still apply. Claude Desktop still sends `name` to your provider. Through an LLM gateway, sessions also assume Claude Sonnet 5's [context window](https://claude.com/docs/third-party/claude-desktop/gateway.md#context-window-and-compaction).

If the ID contains a Claude model version, set `behavesAs` to that same model. If the ID routes to a different model, use an ID without a version. Whatever `behavesAs` says, sessions treat both `acme-claude-sonnet-4-6` and `acme-claude-sonnet-4.6` as Claude Sonnet 4.6. Before Claude Desktop 4.16336.0, sessions treat `acme-claude-sonnet-4.6` as Claude Sonnet 4 and send no effort level. Until every device runs Claude Desktop 4.16336.0 or later, write the model version with hyphens, such as `acme-claude-sonnet-4-6`.

To check a value, go to **Help > Troubleshooting > Generate Diagnostic Report**, click **Export to file**, and open the saved `.zip` file:

* **`model-selection.txt`**: the entry's `behavesAs` line says whether the picker uses the value. `(the picker offers that model's options)` means it does.
* **`managed-config.txt`**: `behavesAs dropped: not an accepted value` under `Parse errors` means the value isn't a model ID. Enter a full ID such as `claude-sonnet-5`, not a family name such as `sonnet`.

Without `behavesAs`, users can't change an unrecognized model's effort level. Its conversations and sessions never run above the `maxEffort` on its entry. When it's the default model, its new conversations and sessions start at [`defaultModelEffort`](https://claude.com/docs/third-party/claude-desktop/configuration#defaultmodeleffort), up to that cap. With only `maxEffort` set, they run at that cap.

## Start every conversation on the default model

Set [`alwaysStartWithDefaultModel`](https://claude.com/docs/third-party/claude-desktop/configuration#alwaysstartwithdefaultmodel) to `true` to start every new Chat conversation, Cowork session, and Code session on the [default model](#model-list-and-default-model) at its [starting effort level](#effort-levels), not on the user's last choice. When the user picks a model or effort level, it applies only for that conversation or session.

If you leave `alwaysStartWithDefaultModel` unset, the default model and its starting effort level apply until a user picks a different model or effort level. Claude Desktop remembers that choice and starts the user's new conversations and sessions from it.

When you turn the setting on, Claude Desktop keeps the choices users saved earlier. If you later turn it off, those choices apply again.

`alwaysStartWithDefaultModel` also applies when [model discovery](https://claude.com/docs/third-party/claude-desktop/configuration.md#modeldiscoveryenabled) fills the picker instead of an `inferenceModels` list.

## Example configuration

The following configuration offers Claude Sonnet 5 and Claude Opus 5. It makes Claude Sonnet 5 the default model at medium effort, caps both models at high effort, and starts every new conversation and session from those defaults:

```json theme={null}
{
  "inferenceModels": [
    { "name": "claude-sonnet-5", "maxEffort": "high" },
    { "name": "claude-opus-5", "maxEffort": "high" }
  ],
  "defaultModelEffort": "medium",
  "alwaysStartWithDefaultModel": true
}
```

With this configuration, a user who starts a new Cowork session sees Claude Sonnet 5 selected at medium effort. The **Effort** control offers low, medium, and high for every entry.

The example is plain JSON, which is the form a [bootstrap server](https://claude.com/docs/third-party/claude-desktop/bootstrap.md) response and the Linux managed file use. For a macOS profile or the Windows registry, encode the same values as the [Value types](https://claude.com/docs/third-party/claude-desktop/configuration-format.md#value-types) section describes.
