Wan 2.6 T2V

    alibaba/wan2.6-t2v
    試驗場

    Generate 720p/1080p video from text prompts and come with synchronized audio tracks. The picture has movie-level aesthetics and complex motion performance, suitable for creative video creation.

    Creative GenerationHigh-Quality GenerationContent GenerationMultimodal Understanding
    模態
    輸入 / 輸出價格
    -- / $0.1 起秒
    上下文
    --
    發布時間
    2026-03-15

    價格

    規格720p1080p
    影片$0.1/ 秒$0.15/ 秒

    快速開始

    可直接貼上執行下方範例程式碼。Gate.AI API 與 OpenAI 相容，多數 SDK 只需替換 base URL；切換模型時，只需修改模型 ID。

    1

    Get your API key

    Sign in to the Gate.AI console and create a new key under "API Keys". Keep it safe and send it via the Authorization header on every request.

    前往控制台建立金鑰
    環境變數
    export GATEAI_API_KEY="YOUR_API_KEY"; export GATEAI_API_URL="https://api.gate.ai/api/v1/videos"
    2

    Make a request

    Send a POST request to the Chat Completions endpoint with a model ID and an array of messages to get a reply.

    POSThttps://api.gate.ai/api/v1/videos
    curl --location "https://api.gate.ai/api/v1/videos" --header "Authorization: Bearer {API_KEY}" --header "Content-Type: application/json" --header "Idempotency-Key: {IDEMPOTENCY_KEY}" --data '{"model":"wan2.6-t2v","prompt":"A golden retriever running on a sunny beach, cinematic camera movement","duration":6,"resolution":"720p","aspect_ratio":"16:9","generate_audio":false,"seed":-1}'
    3

    Handle the response & streaming

    By default a full JSON response is returned. Add "stream": true to the request body to receive incremental chunks over SSE.

    POSThttps://api.gate.ai/api/v1/videos
    JOB_ID=$(curl --silent --location "https://api.gate.ai/api/v1/videos" --header "Authorization: Bearer {API_KEY}" --header "Content-Type: application/json" --header "Idempotency-Key: {IDEMPOTENCY_KEY}" --data '{"model":"wan2.6-t2v","prompt":"A golden retriever running on a sunny beach, cinematic camera movement","duration":6,"resolution":"720p"}' | jq -r '.data.job_id'); curl --location "https://api.gate.ai/api/v1/videos/${JOB_ID}" --header "Authorization: Bearer {API_KEY}"

    端點

    基礎 URL、請求方法與必要請求頭，皆依當前模型的協議模板渲染。

    POSThttps://api.gate.ai/api/v1/videos
    欄位
    值
    Authorization
    驗證請求頭，使用 Bearer {API_KEY} 格式傳遞 API Key
    Content-Type
    請求內容型別，固定為 application/json
    Idempotency-Key
    Optional idempotency key; repeated submissions with the same value do not create duplicate jobs
    model
    Required video model ID; the current model is wan2.6-t2v
    prompt
    Required video description; include subject, action, scene, camera, and style
    duration
    Optional video duration in seconds; supported range depends on the model
    resolution
    Optional output resolution: 480p, 720p, or 1080p
    aspect_ratio
    Optional aspect ratio: 16:9, 4:3, 1:1, 3:4, 9:16, 21:9, or adaptive
    generate_audio
    Optional; whether to generate audio
    seed
    Optional random seed from -1 to 4294967295
    size
    Optional exact output size, such as 1280x720
    input_references
    Optional reference media array for image-to-video, first or last frames, or style transfer
    metadata
    Optional pass-through business object for auditing or source tags
    webhook_url
    Optional callback URL invoked when the job completes or fails

    相關模型

    HappyHorse 1.1 T2V

    Stronger prompt adherence than 1.0 on complex instructions. Generates 3–15 second clips at up to 1080p from a written description, suited for producing creative content directly from a script.

    HappyHorse 1.1 I2V

    Smoother motion than 1.0 across camera moves and body movement. Extends a single starting image into a full shot, outputting 3–15 second clips at up to 1080p.

    HappyHorse 1.1 R2V

    Holds characters more consistent across frames than 1.0. Takes a set of reference images to lock character, scene, and style, outputting 3–15 second clips at up to 1080p.

    HappyHorse 1.0 T2V

    Generates 3–15 second clips at up to 1080p from a written description, across a range of aspect ratios. Suited for taking a script straight to creative content and short-form social video.

    HappyHorse 1.0 I2V

    Extends a single starting image into a full shot, preserving its composition and style, and outputs 3–15 second clips at up to 1080p. Suited for turning still assets into motion.

    HappyHorse 1.0 R2V

    Takes a set of reference images to lock character, scene, and style, holding the subject consistent across shots. Outputs 3–15 second clips at up to 1080p.

    Wan2.6 R2V Flash

    Speed-optimized Wan 2.6 reference-to-video variant with optional audio output, replicating reference-video motion into up to 10 second 720p/1080p clips for fast, cost-effective production.

    Wan 2.6 R2V

    Alibaba Tongyi Wanxiang Wan 2.6 reference-to-video model replicates the actions, effects, and camera movement of a reference video to produce up to 10 second 720p/1080p clips with synchronized audio.

    Wan 2.6 I2V Flash

    Speed-optimized Wan 2.6 image-to-video variant with optional audio output, generating 720p/1080p clips quickly and cost-effectively for high-throughput image animation.

    Wan 2.6 I2V

    Alibaba Tongyi Wanxiang Wan 2.6 image-to-video model animates a reference image into 720p/1080p clips with synchronized audio, preserving subject consistency with cinematic motion.