# Wan 2.5 > Wan 2.5 is Alibaba's video model, previewed in September 2025, that makes clips of up to 10 seconds at up to 1080p from text or a start image and was the first Wan built to generate synced audio with the picture. Unlike Wan 2.1 and 2.2 its weights are closed. On Kenerate AI it costs 15, 30 or 45 credits a second at 480p, 720p or 1080p — 75 credits for a 5-second 480p draft — and the Wan 2.5 image model makes stills for 9 credits. URL: https://kenerateai.com/models/alibaba/wan-2-5 Publisher: Kenerate AI (https://kenerateai.com) Last updated: 18 October 2026 ## Key facts - Official name: Wan 2.5 (Wan2.5-Preview) - API ID: alibaba/wan-2.5 - Maker: Alibaba (Tongyi Wanxiang) - Released: September 2025 - Weights: Closed (hosted only) - Clip length: Text 5 or 10 s · image 3–10 s - Resolution: 480p · 720p · 1080p - Aspect ratios: 16:9 · 9:16 - Audio: Sync to your wav / mp3 - On Kenerate: 15 · 30 · 45 credits a second ## Steps 1. Open the video studio — Go to /app/video and pick Wan 2.5 (the button on this page selects it). Video needs any one-time credit pack. 2. Add a start frame or audio (optional) — Upload the image the clip should start from, and a voice or music file if the clip should follow it. Leave both empty for text to video. 3. Describe the shot — Say who or what is in frame, the action, the camera move and the light. Add a negative prompt for things to avoid. 4. Pick length and resolution — 5 or 10 seconds for text, 3–10 for an image; 480p to draft, 1080p to finish. The credit cost shows before you generate. ## In depth ### Which resolution to use Wan 2.5's price on Kenerate depends only on length and resolution. Prices below are for a 5-second clip: - 480p — 75 credits. Testing a prompt, motion and timing. - 720p — 150 credits. Social clips and previews. - 1080p — 225 credits (450 for 10 seconds). The final render. ### Where Wan 2.5 sits in the Wan family Wan 2.1 (February 2025) and 2.2 (July 2025) are the open-weights releases. Wan 2.5 (September 2025) was the first closed, hosted-only Wan and the first to pair video with synced audio [1][2]. Wan 2.6 followed with 15-second clips, Wan 2.7 with end frames and editing, and Wan 3.0 with 30-second clips and sound. On API platforms Wan 2.5 runs at 480p, 720p and 1080p for up to 10 seconds, with an optional wav or mp3 track to drive the voice or music [3]. Kenerate runs the same alibaba/wan-2.5 model for text to video, image to video and video extend. ### Prompting Wan 2.5 Write one shot per prompt: subject, action, camera move, light and mood, in that order. Use the negative prompt for things you keep seeing and don't want — extra people, text, blur. If the clip should follow speech or music, attach the audio file and describe the speaker or the scene's rhythm; the launch review found music sync weaker than speech, so check timing on a 480p draft first [1]. References: [1] Alibaba's Wan2.5-Preview turns photos and text into videos with matching audio — The Decoder: https://the-decoder.com/alibabas-wan2-5-preview-lets-users-turn-photos-and-text-prompts-into-videos-with-matching-audio/ [2] Wan 2.5 — AI Wiki: https://aiwiki.ai/wiki/wan_2_5 [3] alibaba/wan-2.5 text-to-video — WaveSpeed: https://wavespeed.ai/models/alibaba/wan-2.5/text-to-video ## FAQ Q: What is Wan 2.5? A: Wan 2.5 is Alibaba's AI video model, first shown as Wan2.5-Preview in September 2025. It makes clips of up to 10 seconds at up to 1080p from a text prompt or a start image, and it was the first Wan model built to generate audio — voices, music and effects — in sync with the picture. There is also a Wan 2.5 image model for stills. Q: Is Wan 2.5 open source? A: No. Wan 2.1 and Wan 2.2 have open weights under Apache 2.0, but Wan 2.5 and every later version (2.6, 2.7, 3.0) run only as hosted models through Alibaba Cloud and API platforms. You can't download Wan 2.5 for ComfyUI; you run it online, for example in Kenerate's video studio. Q: How much does Wan 2.5 cost on Kenerate? A: It's billed per second by resolution: 15 credits a second at 480p, 30 at 720p and 45 at 1080p. A 5-second clip costs 75, 150 or 225 credits, and a 10-second 1080p clip 450. Credits come in one-time packs that never expire, starting at $15 for 1,300 credits — no subscription. Q: How long can Wan 2.5 videos be? A: Up to 10 seconds per clip. Text to video takes 5 or 10 seconds; image to video accepts any whole number from 3 to 10. To go longer, use video extend, which adds another 3–10 seconds to an existing clip, or chain clips by starting each from the last frame of the one before. Q: Does Wan 2.5 generate sound? A: Alibaba built Wan 2.5 to make audio and video in one pass, including lip-synced speech, though one launch review found music and drumming drifting out of sync. On Kenerate you can attach your own wav or mp3 track for the clip to follow; there's no sound toggle, so for sound written from the prompt alone use Wan 3.0. Q: Can Wan 2.5 animate an image? A: Yes. Upload a start image in /app/video, choose 3–10 seconds and describe the motion. Wan 2.5 keeps the image as the first frame, which is the most reliable way to keep a product, character or layout as designed. It doesn't take an end frame; Wan 2.7 and Kling 3.0 do. Q: Is Wan 2.5 free? A: Not on Kenerate's free plan: video needs a paid plan, which means buying any one-time credit pack. New accounts get starter credits for images on free-plan models such as Qwen Image 3.0. The Wan 2.5 image model costs 9 credits an image and is not a free-plan model. Q: What is the Wan 2.5 image model? A: It's Alibaba's text-to-image model from the same release, listed in Kenerate's image studio as Wan 2.5. It makes images up to 1440 px a side, supports a negative prompt and a seed, and can edit or blend up to 2 reference images. It costs 9 credits per image and 10.5 per edit. The four examples on this page are its real outputs. Q: Wan 2.5 vs Wan 2.6 vs Wan 3.0 — which should I use? A: Wan 2.5 is the cheapest way to draft Wan video (15 credits a second at 480p, which Wan 2.6 and 2.7 don't offer) and costs the same as them at 1080p (45 a second) when 10 seconds is enough. Wan 2.6 adds 15-second clips and reference images, Wan 2.7 adds editing and more aspect ratios, and Wan 3.0 makes up to 30 seconds with generated sound. Draft on Wan 2.5 at 480p, then move up if you need length or sound. Q: What is alibaba/wan-2.5? A: It's the API name model platforms such as WaveSpeed use for Wan 2.5, with separate text-to-video, image-to-video and video-extend endpoints. On Kenerate you don't need an API key or a provider account: the same model runs in the browser as Wan 2.5 and is billed in credits. ## Related pages - Wan AI video generator: https://kenerateai.com/wan-ai-video-generator - Wan 2.6: https://kenerateai.com/models/alibaba/wan-2-6 - Wan 2.7: https://kenerateai.com/models/alibaba/wan-2-7 - Wan 3.0: https://kenerateai.com/wan-3-0 - Wan 2.2: https://kenerateai.com/wan-2-2 - Wan image models: https://kenerateai.com/model/wan - All AI video models: https://kenerateai.com/ai-video-models ## Sources - Alibaba's Wan2.5-Preview turns photos and text into videos with matching audio — The Decoder: https://the-decoder.com/alibabas-wan2-5-preview-lets-users-turn-photos-and-text-prompts-into-videos-with-matching-audio/ - Wan 2.5 — AI Wiki: https://aiwiki.ai/wiki/wan_2_5 - alibaba/wan-2.5 text-to-video — WaveSpeed: https://wavespeed.ai/models/alibaba/wan-2.5/text-to-video