> ## Documentation Index > Fetch the complete documentation index at: https://docs.goenhance.ai/llms.txt > Use this file to discover all available pages before exploring further. # Anime Video Upscaler > Real-ESRGAN anime video upscaling: bring an existing anime clip up to 1080p, 2K or 4K. **How it differs from `video-upscaler`** — this endpoint runs a model trained specifically on animation. Line art stays sharp and flat colour areas stay flat, instead of being smoothed into the mushy texture a general-purpose upscaler tends to produce on drawn content. For live action, use `video-upscaler` instead. **Pricing** — per second of the **source video**, by target resolution (USD at $0.02/token): | resolution | tokens/s | USD/s | |---|---|---| | 1080p | 1 | $0.02 | | 2K | 2 | $0.04 | | 4K | 4 | $0.08 | A 60-second clip therefore costs 60 tokens at 1080p (= $1.20). The same clip costs 120 tokens at 2K (= $2.40). At 4K it costs 240 tokens (= $4.80). ⚠️ **There is no `duration` parameter.** The source video is measured server-side and the whole clip is upscaled; the measured length, rounded up to whole seconds, is what you are charged for. **Source video requirements:** | | | |---|---| | max length | **180s** — the same at every target resolution | | max short side | **1080 pixels** (portrait or landscape) | | max file size | 300MB | | codec | av1 is not supported | A clip that breaks any of these is rejected before any tokens are deducted — it is never silently truncated. The short-side limit is not an arbitrary quota: a source that is already above 1080p has nothing left to recover, so upscaling it would cost you the top rate for what amounts to a resize. **Output** — duration, frame rate and aspect ratio all follow the source; no frames are interpolated or dropped. The result carries no watermark. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the upscaled video. ## OpenAPI ````yaml api-reference/video-generations/openapi-anime-upscaler.json POST /api/v1/videos/generations openapi: 3.1.0 info: title: GoEnhance API - Anime Video Upscaler description: Upscale an anime clip to 1080p, 2K or 4K. version: 1.0.0 servers: - url: https://api.goenhance.ai security: [] paths: /api/v1/videos/generations: post: tags: - VideoGenerations summary: Anime Video Upscaler description: >- Real-ESRGAN anime video upscaling: bring an existing anime clip up to 1080p, 2K or 4K. **How it differs from `video-upscaler`** — this endpoint runs a model trained specifically on animation. Line art stays sharp and flat colour areas stay flat, instead of being smoothed into the mushy texture a general-purpose upscaler tends to produce on drawn content. For live action, use `video-upscaler` instead. **Pricing** — per second of the **source video**, by target resolution (USD at $0.02/token): | resolution | tokens/s | USD/s | |---|---|---| | 1080p | 1 | $0.02 | | 2K | 2 | $0.04 | | 4K | 4 | $0.08 | A 60-second clip therefore costs 60 tokens at 1080p (= $1.20). The same clip costs 120 tokens at 2K (= $2.40). At 4K it costs 240 tokens (= $4.80). ⚠️ **There is no `duration` parameter.** The source video is measured server-side and the whole clip is upscaled; the measured length, rounded up to whole seconds, is what you are charged for. **Source video requirements:** | | | |---|---| | max length | **180s** — the same at every target resolution | | max short side | **1080 pixels** (portrait or landscape) | | max file size | 300MB | | codec | av1 is not supported | A clip that breaks any of these is rejected before any tokens are deducted — it is never silently truncated. The short-side limit is not an arbitrary quota: a source that is already above 1080p has nothing left to recover, so upscaling it would cost you the top rate for what amounts to a resize. **Output** — duration, frame rate and aspect ratio all follow the source; no frames are interpolated or dropped. The result carries no watermark. Returns an `img_uuid`; poll GET /api/v1/jobs/detail (or use `custom_callback_url`) to get the upscaled video. parameters: - name: Authorization in: header description: '' required: false example: '{{Authorization}}' schema: type: string requestBody: content: application/json: schema: type: object properties: model: type: string enum: - anime-upscaler description: Model name. Must be `anime-upscaler`. video_url: type: string format: uri description: >- Source anime video URL. Up to 300MB and 180 seconds, short side at most 1080 pixels; av1 is not supported. The whole clip is upscaled and its measured duration is the billing basis. resolution: type: string enum: - 1080p - 2k - 4k description: >- Target resolution. Defaults to `2k`. The maximum source length is 180s at every resolution — unlike `video-upscaler`, picking `4k` does not shorten it. custom_callback_url: type: string format: uri description: >- Optional. A publicly accessible HTTPS URL. When the task status changes (processing / success / failed), GoEnhance sends a POST request to this URL. The request body is identical to the response of GET /api/v1/jobs/detail. If your server does not respond with HTTP 200, the notification is retried up to 3 times, with a 3-second timeout per attempt. example: https://your-server.com/goenhance/callback required: - model - video_url example: model: anime-upscaler video_url: https://your-cdn.com/anime-clip.mp4 resolution: 2k responses: '200': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string data: type: object properties: img_uuid: type: string required: - img_uuid required: - code - msg - data examples: '1': summary: Success value: code: 0 msg: Success data: img_uuid: c12b656c-747a-44fd-9c80-add79b0c52d5 '2': summary: Invalid duration value: code: -1 msg: duration (30s) exceeds the reference video length (12s). '3': summary: Insufficient tokens value: code: 100 msg: tokens is not enough quota: summary: API key quota exceeded value: code: 101 msg: 'API key quota exceeded: 4990 of 5000 tokens used (monthly)' headers: {} '401': description: '' content: application/json: schema: type: object properties: code: type: integer msg: type: string required: - code - msg headers: {} deprecated: false security: [] ````