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

# mulerouter params

> Show every parameter accepted by a model endpoint

Inspect the parameters of a specific model endpoint — names, types, default
values, enum choices, and which ones are required.

## Synopsis

```bash theme={null}
mulerouter params <endpoint> [--json]
```

## Endpoint identifier

The `<endpoint>` argument accepts two forms:

| Form                          | Behavior                                                                            |
| ----------------------------- | ----------------------------------------------------------------------------------- |
| `<provider>/<model>`          | Auto-resolves the action if the model has exactly one                               |
| `<provider>/<model>/<action>` | Explicit action — required when a model has multiple (e.g. `generation` and `edit`) |

If a two-part identifier is ambiguous, `params` will list the available actions
and exit with an error.

## Options

| Option   | Description                                            |
| -------- | ------------------------------------------------------ |
| `--json` | Output as JSON (useful for codegen or LLM consumption) |

## Examples

```bash theme={null}
mulerouter params alibaba/wan2.6-t2v
mulerouter params google/nano-banana-2/edit
mulerouter params openai/gpt-image-2/generation --json
```

## Text output

```
alibaba/wan2.6-t2v/generation
Wan2.6 Text-to-Video: Generate videos from text prompts with multi-shot, audio, and resolution control

Parameters:
------------------------------------------------------------

  --prompt (required)
    Type: string
    Text prompt describing the video to generate

  --size [default: 1280*720] [choices: 1280*720, 960*960, 720*1280, 1920*1080, ...]
    Type: string
    Video resolution

  --duration [default: 5] [choices: 5, 10, 15]
    Type: integer
    Video duration in seconds

  ...

API Path: /vendors/alibaba/v1/wan2.6-t2v/generation
Output Type: video
Result Key: videos
Available On: mulerouter, mulerun
```

The trailing metadata block tells you:

* **API Path** — the upstream URL the CLI will `POST` to (also useful for
  [`mulerouter status`](/docs/cli/commands/status))
* **Result Key** — the JSON key under which result URLs appear (`videos`,
  `images`, `audios`, ...)
* **Available On** — which sites expose this endpoint

## JSON output

```json theme={null}
{
  "model_id": "alibaba/wan2.6-t2v",
  "action": "generation",
  "description": "...",
  "api_path": "/vendors/alibaba/v1/wan2.6-t2v/generation",
  "output_type": "video",
  "result_key": "videos",
  "available_on": ["mulerouter", "mulerun"],
  "parameters": [
    {
      "name": "prompt",
      "type": "string",
      "description": "Text prompt describing the video to generate",
      "required": true
    },
    {
      "name": "duration",
      "type": "integer",
      "description": "Video duration in seconds",
      "required": false,
      "default": 5,
      "enum": [5, 10, 15]
    }
  ]
}
```

## Naming convention

Parameter names in the catalog use `snake_case` (matching the JSON request
body), while CLI flags use `--kebab-case`. The CLI converts between the two
automatically.

| Catalog name      | CLI flag            |
| ----------------- | ------------------- |
| `prompt`          | `--prompt`          |
| `negative_prompt` | `--negative-prompt` |
| `aspect_ratio`    | `--aspect-ratio`    |
| `first_frame`     | `--first-frame`     |

## See also

* [`mulerouter run`](/docs/cli/commands/run) — actually invoke the endpoint
* [`mulerouter list`](/docs/cli/commands/list) — find an endpoint identifier