docs: fix mangled models link in video-generation guide

guides/overview/multimodal/video-generation.mdx

@@ -8,7 +8,7 @@
 og:image: https://openrouter.ai/dynamic-og?title=OpenRouter%20Video%20Generation&description=Generate%20videos%20using%20AI%20models%20through%20the%20OpenRouter%20API.
 og:image:width: 1200
 og:image:height: 630
 twitter:card: summary_large_image
 twitter:site: '@OpenRouter'
 noindex: false
 nofollow: false
@@ -21,7 +21,7 @@
 } from '/snippets/exports/constants.mdx';
 import OpenRouterVideoSkill from "/snippets/openrouter-video-skill.mdx";
 
-OpenRouter supports video generation from text prompts (and optional reference images) via a dedicated asynchronous API. You can find the supported models, their capabilities, and pricing by filtering our [model list by video output](https://openrouter.ai/docs/guides/overview/models?output_modalities=video).
+OpenRouter supports video generation from text prompts (and optional reference images) via a dedicated asynchronous API. You can find the supported models, their capabilities, and pricing by filtering our [model list by video output](https://openrouter.ai/models?output_modalities=video).
 
 <Tip>
   Adding video generation to an app? The
@@ -63,7 +63,7 @@
         "per-video-second": "0.50",
         "per-video-second-1080p": "0.75"
       },
       "allowed_passthrough_parameters": ["output_config"]
     }
   ]
 }
@@ -246,7 +246,7 @@
 | `generate_audio` | boolean | No | Whether to generate audio alongside the video. Defaults to `true` for models that support audio output |
 | `seed` | integer | No | Seed for deterministic generation (not guaranteed by all providers) |
 | `callback_url` | string | No | URL to receive a webhook notification when the job completes. Overrides the workspace-level default callback URL if set. Must be HTTPS |
 | `provider` | object | No | Provider-specific passthrough configuration |
 
 ### Supported Resolutions
 
@@ -287,7 +287,7 @@
 precedence and the request is treated as
 image-to-video.
 
 #### Image-to-Video (frame_images)
 
 ```json lines
 {
@@ -306,7 +306,7 @@
 }
 ```
 
 #### Reference-to-Video (input_references)
 
 ```json lines
 {
@@ -345,7 +345,7 @@
 }
 ```
 
 Use the [Video Models API](#via-the-video-models-api) to check which passthrough parameters each model supports via the `allowed_passthrough_parameters` field.
 
 ## Response Format
 
@@ -414,7 +414,7 @@
 When a job reaches a terminal state, a POST request is sent to the callback
 URL with an event envelope. Each delivery also carries an
 `X-OpenRouter-Idempotency-Key` header of the form `<job_id>-<status>` for
 safe retry deduplication.
 
 `video.generation.completed`: