# Wan 2.6 Video-to-Video — Atlas Cloud API > A speed-optimized video-to-video option that prioritizes lower latency while retaining strong visual fidelity. Ideal for iteration, batch generation, and prompt testing. This is the machine-readable API reference for **Wan 2.6 Video-to-Video** on Atlas Cloud, a unified API platform for 400+ AI models across text, image, video, audio and 3D. - **Model ID**: `alibaba/wan-2.6/video-to-video` - **Built by**: Alibaba - **Modality**: Video - **Model page**: https://www.atlascloud.ai/models/alibaba/wan-2.6/video-to-video - **API key**: https://www.atlascloud.ai/console/api-keys - **Docs**: https://www.atlascloud.ai/docs ## Pricing on Atlas Cloud - $0.07 per second of generated video - Pay-as-you-go. No minimum spend, no subscription required. > **These are the authoritative Atlas Cloud rates for this model.** Any price that > appears in the vendor description further down refers to a different platform or > a different model variant and does not apply here. ## Use this model from an AI agent Atlas Cloud ships three first-party integration surfaces. All three authenticate with the same API key via the `ATLASCLOUD_API_KEY` environment variable. ### MCP server The official MCP server (`atlascloud-mcp`) exposes this model to any MCP-compatible host — Claude Code, OpenAI Codex, Cursor, Gemini CLI, Goose, Claude Desktop. One-line install: ```bash # Claude Code claude mcp add atlascloud -- npx -y atlascloud-mcp # OpenAI Codex CLI codex mcp add atlascloud -- npx -y atlascloud-mcp # Gemini CLI gemini mcp add atlascloud -- npx -y atlascloud-mcp export ATLASCLOUD_API_KEY="your-api-key" ``` Then ask in plain English; the agent calls `atlas_generate_video` with `model: "alibaba/wan-2.6/video-to-video"`. The server fetches each model's schema and validates parameters before submitting, so invalid requests fail fast without spending credits. MCP docs: https://www.atlascloud.ai/docs/mcp-server ### Agent Skills `atlas-cloud-skills` is a portable skill package (API reference, code templates in Python / Node.js / cURL, model IDs with pricing) for Claude Code, Cursor, Codex and 12+ other agents: ```bash npx skills add AtlasCloudAI/atlas-cloud-skills export ATLASCLOUD_API_KEY="your-api-key" ``` Skills docs: https://www.atlascloud.ai/docs/skills ### CLI The `atlas` binary runs Atlas Cloud from a terminal or CI script. Async media jobs are polled and downloaded automatically (use `--no-download` when a script only needs the output URLs): ```bash # Install (Homebrew, npm, or shell installer) brew install AtlasCloudAI/tap/atlascloud # npm install -g atlascloud-cli # curl -fsSL https://raw.githubusercontent.com/AtlasCloudAI/cli/main/install.sh | sh atlas auth login atlas generate video alibaba/wan-2.6/video-to-video -p "Your prompt here" ``` CLI docs: https://www.atlascloud.ai/docs/cli ## HTTP API reference - **Submit endpoint (POST)**: `https://api.atlascloud.ai/api/v1/model/generateVideo` — start an async generation; returns a `prediction_id` - **Poll endpoint (GET)**: `https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}` — poll this until the prediction finishes - **Model ID**: `alibaba/wan-2.6/video-to-video` ## API Information This model can be used via our HTTP API or more conveniently via our client libraries. See the input and output schema below, as well as the usage examples. ### Input Schema The API accepts the following input parameters: - **`model`** (`string`, _required_): model name - Default: `"alibaba/wan-2.6/video-to-video"` - **`prompt`** (`string`, _required_): The prompt for generating the output. Follow the order of the reference videos and refer to each one as characterX. For example, if there are two reference videos, write the prompt as ‘character1 singing by the roadside, character2 dancing beside them.’ For a single reference video, you should still use character1 with the number included. - **`negative_prompt`** (`string`, _optional_): Negative prompt for the generation. - **`videos`** (`array[string]`, _required_): List of URLs of input videos for editing. Each video should be less than 100MB, 2-30s, mp4 or mov. For portraits, it is recommended to use close-up shots of the head, filmed from multiple angles, combined with audio for timbre reference. For non-human anthropomorphic subjects such as pets, shoot from multiple angles; if a fixed timbre is needed, you can add an audio track input. For other inanimate objects, simply record multi-angle videos. The richer the subject information, the better the reference effect. - Min items: 1 - Max items: 3 - **`size`** (`string`, _required_): The size of the generated media in pixels (width*height). - Default: `"1280*720"` - Options: "1280*720", "720*1280", "960*960", "1088*832", "832*1088", "1920*1080", "1080*1920", "1440*1440", "1632*1248", "1248*1632" - **`duration`** (`integer`, _optional_): The duration of the generated media in seconds. - Default: `5` - Options: 5, 10 - **`enable_prompt_expansion`** (`boolean`, _optional_): If set to true, the prompt optimizer will be enabled. - Default: `true` - **`shot_type`** (`string`, _optional_): Generate video in multi camera angles, only works when set enable_prompt_expansion to true. - Default: `"multi"` - Options: "multi", "single" - **`seed`** (`integer`, _optional_): The random seed to use for the generation. -1 means a random seed will be used. - Default: `-1` **Required Parameters Example**: ```json { "model": "alibaba/wan-2.6/video-to-video", "prompt": "", "size": "1280*720", "videos": [ "" ] } ``` **Full Example**: ```json { "model": "alibaba/wan-2.6/video-to-video", "prompt": "", "negative_prompt": "", "videos": [ "" ], "size": "1280*720", "duration": 5, "enable_prompt_expansion": true, "shot_type": "multi", "seed": -1 } ``` ### Output Schema The API returns the following output format: - **`created_at`** (`string`, _optional_): ISO timestamp of when the request was created (e.g., “2023-04-01T12:34:56.789Z”). - **`has_nsfw_contents`** (`array[boolean]`, _optional_): Array of boolean values indicating NSFW detection for each output. - **`id`** (`string`, _optional_): Unique identifier for the prediction, the ID of the prediction to get. - **`model`** (`string`, _optional_): Model ID used for the prediction. - **`outputs`** (`array[object]`, _optional_): Array of URLs to the generated content (empty when status is not completed). - **`status`** (`string`, _optional_): Status of the task: created, processing, completed, or failed. - **`urls`** (`object`, _optional_): Object containing related API endpoints. **Example Response**: ```json { "created_at": "", "has_nsfw_contents": [], "id": "", "model": "", "outputs": [], "status": "", "urls": {} } ``` ## Usage Examples ### cURL ```bash # Step 1: Start generation (async) curl -X POST "https://api.atlascloud.ai/api/v1/model/generateVideo" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "alibaba/wan-2.6/video-to-video", "prompt": "", "negative_prompt": "", "videos": [ "" ], "size": "1280*720", "duration": 5, "enable_prompt_expansion": true, "shot_type": "multi", "seed": -1 }' # Response will contain: {"code": 200, "data": {"id": "prediction_id", "status": "processing"}} # Step 2: Poll for result (replace {prediction_id} with the id returned above) curl -X GET "https://api.atlascloud.ai/api/v1/model/prediction/{prediction_id}" \ -H "Authorization: Bearer $ATLASCLOUD_API_KEY" # Keep polling until status is "completed", "succeeded" or "failed" # When completed, outputs will contain the generated content URL(s) ``` ## Additional Resources ### Documentation - [Model Playground](https://www.atlascloud.ai/models/alibaba/wan-2.6/video-to-video) ## About this model _Vendor-supplied description. Any pricing or endpoint mentioned below refers to_ _other platforms — use the Atlas Cloud values above._ ### Alibaba WAN 2.6 Video-to-Video Model Alibaba WAN 2.6 is an advanced Video-to-Video model provided by Alibaba Cloud's DashScope platform. This model generates high-quality 480p/720p/1080p videos from text prompts. #### What makes it stand out? - **More affordable:** Wan 2.6 is more streamlined and cost-effective - reducing creator expenses and offering more options. - **One-pass A/V sync:** Wan 2.6 creates a fully synchronized video (audio/voiceover + lip-sync) from a single, well-structured prompt - no separate recording or manual alignment required. - **Multilingual friendly:** Wan 2.6 reliably processes like Chinese prompts for A/V-synced videos. - **Longer duration & more video size options:** Wan 2.6 delivers up to 10 seconds and 6 aspect/size options, enabling more storytelling room and publishing flexibility. - **Multi-shot storytelling:** Generates cohesive multi-shot narratives, keeping key details consistent across shots and offering auto shot-split for simple prompts. - **Video reference generation:** Uses a reference video's appearance and voice to guide new videos; supports human or arbitrary subjects, single or dual performers. - **15s long videos:** Produces videos up to 15 seconds, expanding temporal capacity for richer storytelling. #### Designed For - **Marketing teams:** Fast, polished demos/tutorials—low cost, consistent style. - **Global enterprises:** Multilingual, lip-synced videos with subtitles for efficient localization. - **Storytellers & YouTubers:** Immersive narratives while maintaining cadence and quality—driving growth. - **Corporate training teams:** HD videos over docs—clearer key points, better communication. #### Pricing The table below lists prices for easy comparsion. _(Description truncated. Full text on the model page.)_ --- Atlas Cloud — one API for 400+ AI models. Model page: https://www.atlascloud.ai/models/alibaba/wan-2.6/video-to-video · Docs: https://www.atlascloud.ai/docs