Alibaba · Video
OpenClaw x Wan
Wan is Alibaba's full-spectrum video and image model suite, one of the most complete open-weight video families available. Through RunAPI, all Wan versions share a single key and unified billing.
公開版本與端點
| 模型 ID | 版本 | 端點 | 起始價格 | 模型目錄 |
|---|---|---|---|---|
wan-2.2-a14b-image-to-video-turbo | Image-anchored video on the 2.2 architecture | /api/v1/wan/image_to_video | $0.400 | 模型詳情 |
wan-2.2-a14b-speech-to-video-turbo | Audio input drives video motion and lip-sync | /api/v1/wan/speech_to_video | $0.240 | 模型詳情 |
wan-2.2-a14b-text-to-video-turbo | Open-source A14B MoE; baseline quality | /api/v1/wan/text_to_video | $0.400 | 模型詳情 |
wan-2.2-animate-move | Specialized motion animation on 2.2 base | /api/v1/wan/animate | $0.130 | 模型詳情 |
wan-2.2-animate-replace | Subject replacement animation on 2.2 base | /api/v1/wan/animate | $0.130 | 模型詳情 |
wan-2.5-image-to-video | Image-anchored with native audio on 2.5 | /api/v1/wan/image_to_video | $0.120 | 模型詳情 |
wan-2.5-text-to-video | Native audio generation + better motion realism vs 2.2 | /api/v1/wan/text_to_video | $0.120 | 模型詳情 |
wan-2.6-edit-video | Video editing with subject + camera control | /api/v1/wan/edit_video | $0.140 | 模型詳情 |
wan-2.6-flash-edit-video | Speed-optimized 2.6 video editing | /api/v1/wan/edit_video | $0.300 | 模型詳情 |
wan-2.6-flash-image-to-video | Speed-optimized 2.6; lower cost, faster inference | /api/v1/wan/image_to_video | $9.44 | 模型詳情 |
wan-2.6-image-to-video | Image-anchored with 2.6 scene continuity | /api/v1/wan/image_to_video | $0.580 | 模型詳情 |
wan-2.6-text-to-video | Improved scene continuity + complex scene support | /api/v1/wan/text_to_video | $0.580 | 模型詳情 |
wan-2.7-edit-video | wan-2.7-edit-video | /api/v1/wan/edit_video | $0.160 | 模型詳情 |
wan-2.7-image | Standard image generation on 2.7 architecture | /api/v1/wan/text_to_image | $0.050 | 模型詳情 |
wan-2.7-image-pro | 3×3 multi-angle image grid; highest quality image output | /api/v1/wan/text_to_image | $0.120 | 模型詳情 |
wan-2.7-image-to-video | Image-anchored with 2.7 multi-ref support | /api/v1/wan/image_to_video | $0.160 | 模型詳情 |
wan-2.7-r2v | R2V text-to-video with character appearance + voice references | /api/v1/wan/text_to_video | $0.160 | 模型詳情 |
wan-2.7-text-to-video | First-and-last-frame control; 5 simultaneous video refs | /api/v1/wan/text_to_video | $0.160 | 模型詳情 |
設定
指南端點: <endpoint>
選擇 <model-id> 後，依端點的公開輸入契約產生請求。驗證
選擇 <model-id> 後產生驗證命令。使用流程
- 1. 選擇模型 ID
選擇公開模型 ID，並查看其端點與目前起始價格。
- 2. 設定 RunAPI
呼叫端點前設定 RUNAPI_API_KEY。
- 3. 驗證結果
對非同步端點輪詢同一路徑，直到 Task 進入終態。
常見問題
應該使用哪個模型 ID？
從版本表選擇公開模型 ID。每個 ID 可用的端點均列於相應資料列。
本指南會設定聊天模型嗎？
不會。此 Model Line 使用頁面所示的端點流程，不會被描述為 Agent 聊天模型。