Kling 3.0 Omni

    kling/kling-v3-omni

    Fully multimodal variant of the 3.0 line, accepting text, image, and video references in a single generation, with voice-driven characters and native audio.

    Creative GenerationHigh-Quality GenerationContent GenerationMultimodal Understanding
    Modality
    Input / Output Pricing
    -- / $0.084 fromsecond
    Context
    --
    Release date
    2026-02-25

    Pricing

    Specification720P1080P
    Video (audio output and no video input)$0.112/ second$0.14/ second
    Video (no audio output and no video input)$0.084/ second$0.112/ second
    Video (no audio output and video input)$0.126/ second$0.168/ second

    Quick Start

    Paste and run the sample code below. The Gate.AI API is OpenAI-compatible—most SDKs only need a new base URL. To switch models, change the model 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.

    Create a key in the console
    Environment variable
    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":"kling-v3-omni","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=$(curl --silent --location "https://api.gate.ai/api/v1/videos" --header "Authorization: Bearer {API_KEY}" --header "Content-Type: application/json" --header "Idempotency-Key: {IDEMPOTENCY_KEY}" --data '{"model":"kling-v3-omni","prompt":"A golden retriever running on a sunny beach, cinematic camera movement","duration":6,"resolution":"720p"}' | jq -r '.data.job_id'); curl --location "https://api.gate.ai/api/v1/videos/${JOB_ID}" --header "Authorization: Bearer {API_KEY}"

    Endpoint

    Base URL, method, and required headers are rendered from the active protocol template for this model.

    POSThttps://api.gate.ai/api/v1/videos
    Field
    Value
    Authorization
    Authentication header containing the API key in the format Bearer {API_KEY}
    Content-Type
    Request content type, fixed to 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 kling-v3-omni
    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

    Related Models

    Kling 3.0 Turbo

    Speed-and-cost tier of the 3.0 line, covering text-to-video and first-frame image-to-video with multi-shot output. Suited for high-volume production.

    Kling 3.0

    Core model of the 3.0 line, with first- and last-frame control, multi-shot storytelling, and native audio produced in the same pass. Suited for finished short-form work.

    Kling 2.6

    First version to add native audio, producing visuals, voiceover, sound effects, and ambience in one pass. Suited for finished clips up to 10 seconds.

    Kling O1

    Cinematic-oriented model with first- and last-frame control and video reference input, including edits driven by an existing clip. Suited for narrative shot sequences.

    Kling 2.1

    Kling 2.1 image-to-video generation supports first and last frame control.

    Kling 2.5 Turbo

    Cost-efficient tier in the 2.5 generation, with improved prompt adherence and physics under large-amplitude motion. Outputs silent 5- or 10-second clips.

    Kling 2.1 Master

    Quality-oriented tier of the 2.1 line, tuned for motion performance and semantic responsiveness. Supports text-to-video and image-to-video, suited for single-shot clips.

    Kling 2.0 Master

    Flagship of the 2.0 line, tuned for instruction following and cinematic aesthetics, with stylized effect presets. Outputs 1080p only.

    Kling 1.6

    Kling 1.6 supports text, first or last frame, and multi-reference-image video generation.

    Kling 1.5

    The oldest generation still available, limited to image-to-video with first- and last-frame control and no multi-image reference. Suited for basic, cost-sensitive clip generation.