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

# rig ai defaults

> Show account-level AI defaults, or update them with any flag

Available **local and workspace**. Reference source: CLI `0.13.0-rc.5` (`824aefd6ad16`).

With no flags, shows your account's default AI mode, provider, and model. Passing `--mode`, `--provider`, or `--model` changes only those fields. Inside a workspace the defaults can be read but not changed.

## Examples

Show the current defaults.

```bash theme={null}
rig ai defaults
```

Change the default provider and model; the mode is left as it is.

```bash theme={null}
rig ai defaults --provider anthropic --model claude-sonnet-4-20250514
```

Inspect the supported arguments before running this command. Help is offline and does not modify resources.

```bash theme={null}
rig ai defaults --help
```

## Local syntax

```text theme={null}
Usage: rigbox ai defaults [OPTIONS]
```

### Arguments and flags

| Argument | Description | Details |
| - | - | - |
| `-p, --provider` | Default provider: google, openai, or anthropic | Value: PROVIDER |
| `-m, --model` | Default model id (e.g. claude-sonnet-4-20250514) | Value: MODEL |
| `--mode` | Default AI mode: managed or byok | Value: MODE; Choices: managed, byok |
| `--output` | Output format \[default: human, or `rig config set output …`] | Global; Value: OUTPUT; Choices: human, json, yaml, text, table |
| `--query` | Filter output with a JMESPath expression | Global; Value: JMESPATH |
| `--cli-input-json` | Read inputs from a JSON file or '-' (stdin) | Global; Value: FILE |
| `--cli-input-yaml` | Read inputs from a YAML file or '-' (stdin) | Global; Value: FILE; Conflicts: cli\_input\_json |
| `--generate-cli-skeleton` | Print a fillable input template, then exit | Global; Default: false |
| `--no-pager` | Do not pipe help output through a pager | Global; Default: false |
| `-v, --verbose` | Verbose diagnostics on stderr: per-phase deploy tracing, job-poll status, and transport commands. Useful for debugging a slow or stuck `rig deploy` | Global; Default: false |
| `-h, --help` | Print help | |

> **Complete command help**
>
> ```text theme={null}
> Show account-level AI defaults, or update them with any flag
>
> Usage: rigbox ai defaults [OPTIONS]
>
> Options:
>       --output <OUTPUT>
>           Output format [default: human, or `rig config set output …`]
>
>           [possible values: human, json, yaml, text, table]
>
>   -p, --provider <PROVIDER>
>           Default provider: google, openai, or anthropic
>
>   -m, --model <MODEL>
>           Default model id (e.g. claude-sonnet-4-20250514)
>
>       --query <JMESPATH>
>           Filter output with a JMESPath expression
>
>       --cli-input-json <FILE>
>           Read inputs from a JSON file or '-' (stdin)
>
>       --mode <MODE>
>           Default AI mode: managed or byok
>
>           [possible values: managed, byok]
>
>       --cli-input-yaml <FILE>
>           Read inputs from a YAML file or '-' (stdin)
>
>       --generate-cli-skeleton
>           Print a fillable input template, then exit
>
>       --no-pager
>           Do not pipe help output through a pager
>
>   -v, --verbose
>           Verbose diagnostics on stderr: per-phase deploy tracing, job-poll status, and transport commands. Useful for debugging a slow or stuck `rig deploy`
>
>   -h, --help
>           Print help
> ```

## Workspace syntax

```text theme={null}
Usage: rigbox ai defaults [OPTIONS]
```

### Arguments and flags

| Argument | Description | Details |
| - | - | - |
| `-p, --provider` | Default provider: google, openai, or anthropic | Value: PROVIDER |
| `-m, --model` | Default model id (e.g. claude-sonnet-4-20250514) | Value: MODEL |
| `--mode` | Default AI mode: managed or byok | Value: MODE; Choices: managed, byok |
| `--output` | Output format \[default: human, or `rig config set output …`] | Global; Value: OUTPUT; Choices: human, json, yaml, text, table |
| `--query` | Filter output with a JMESPath expression | Global; Value: JMESPATH |
| `--no-pager` | Do not pipe help output through a pager | Global; Default: false |
| `-v, --verbose` | Verbose diagnostics on stderr (per-phase deploy tracing, job-poll status) | Global; Default: false |
| `-h, --help` | Print help | |

> **Complete command help**
>
> ```text theme={null}
> Show account-level AI defaults, or update them with any flag
>
> Usage: rigbox ai defaults [OPTIONS]
>
> Options:
>       --output <OUTPUT>
>           Output format [default: human, or `rig config set output …`]
>
>           [possible values: human, json, yaml, text, table]
>
>   -p, --provider <PROVIDER>
>           Default provider: google, openai, or anthropic
>
>   -m, --model <MODEL>
>           Default model id (e.g. claude-sonnet-4-20250514)
>
>       --query <JMESPATH>
>           Filter output with a JMESPath expression
>
>       --mode <MODE>
>           Default AI mode: managed or byok
>
>           [possible values: managed, byok]
>
>       --no-pager
>           Do not pipe help output through a pager
>
>   -v, --verbose
>           Verbose diagnostics on stderr (per-phase deploy tracing, job-poll status)
>
>   -h, --help
>           Print help
> ```


This documentation is built and hosted on [Mintlify](https://mintlify.com), a developer documentation platform.