Create video

March 24, 2025 (November 16, 2026)

Table of contents

  1. Request Headers
  2. Request Body
    1. Parameters
    2. Input image paths and templates
  3. Responses
  4. Model
  5. Examples
  6. Try It

This endpoint supports both text-to-video (t2v) and image-to-video (i2v) modes.

Supported models (see Model Capabilities for per-model constraints):

  • Native PixVerse: v6 (default), v5.6, v5.5, v5, v5-fast, pixverse-c1
  • Third-party: seedance-2.5, seedance-2.5-flash, seedance-2.5-draft, seedance-2.0, seedance-2.0-fast, seedance-2.0-mini, kling-4.0, kling-o3, kling-v3, grok-imagine, grok-imagine-1.5, veo-3.1-lite, veo-3.1-standard, veo-3.1-fast, happyhorse-1.0, minimax-h3, minimax-h3-max, gemini-omni-flash, flux-3.0, wan-3.0

seedance-2.5-draft makes a cheap 480p draft of a Seedance 2.5 video. When you like it, POST videos/create-final renders the same video at 1080p or 4K, for up to 14 days.

Sora 2 is no longer available: OpenAI shut it down on September 24, 2026.

For dedicated image generation, see POST images/create.

To upload prompt image use POST files.

https://api.useapi.net/v2/pixverse/videos/create

Request Headers
Authorization: Bearer {API token}
Content-Type: application/json
# Alternatively you can use multipart/form-data
# Content-Type: multipart/form-data
Request Body
  • {
        "model": "v6",
        "prompt": "A red panda eating bamboo in a misty forest",
        "duration": 5,
        "quality": "720p",
        "aspect_ratio": "16:9"
    }
    
  • {
        "model": "v6",
        "prompt": "The subject turns and smiles at camera",
        "first_frame_path": "upload/eb20c63d-…png",
        "duration": 5,
        "quality": "720p"
    }
    
  • {
        "template_id": 326733946317888,
        "first_frame_path": "upload/a-…jpeg",
        "last_frame_path": "upload/b-…jpeg"
    }
    
  • {
        "template_id": 384628677917440,
        "prompt": "A warm family reunion in a sunlit backyard.",
        "frame_1_path": "upload/a-…jpeg",
        "frame_2_path": "upload/b-…jpeg",
        "frame_3_path": "upload/c-…jpeg",
        "frame_4_path": "upload/d-…jpeg",
        "frame_5_path": "upload/e-…jpeg"
    }
    
Parameters
  • email is optional, if not specified API will randomly select account from available accounts.

  • model is optional. Default: v6. Supported values — native PixVerse: v6, v5.6, v5.5, v5, v5-fast, pixverse-c1. Third-party: seedance-2.5, seedance-2.5-flash, seedance-2.5-draft, seedance-2.0, seedance-2.0-fast, seedance-2.0-mini, kling-4.0, kling-o3, kling-v3, grok-imagine, grok-imagine-1.5, veo-3.1-lite, veo-3.1-standard, veo-3.1-fast, happyhorse-1.0, minimax-h3, minimax-h3-max, gemini-omni-flash, flux-3.0, wan-3.0. See Model Capabilities for per-model quality, duration, and aspect-ratio constraints. grok-imagine-1.5 is image-to-video only — it requires first_frame_path and rejects no-image (text-to-video) requests. Ignored when template_id is set — see notes.

  • prompt is optional, describe your video.
    Maximum length 5,000 characters, 20,000 for wan-3.0, 15,000 for seedance-2.5, seedance-2.5-flash and seedance-2.5-draft, 7,000 for minimax-h3 and minimax-h3-max, 4,096 for grok-imagine and grok-imagine-1.5, 4,000 for flux-3.0, 3,800 for gemini-omni-flash, 3,500 for veo-3.1-lite, veo-3.1-standard and veo-3.1-fast, and 2,500 for kling-4.0, kling-o3, kling-v3 and happyhorse-1.0.

  • first_frame_path, last_frame_path, frame_1_path, frame_2_path, frame_3_path, frame_4_path, frame_5_path are optional input image paths. Upload images via POST /files first and use the returned path value. Two interchangeable forms exist for providing image paths and the count rules depend on effect_type — see notes for full rules.

  • template_id is optional, effect template id from GET videos/effects. When set, the template controls model/duration/quality — see notes.

  • duration is optional for the native models v6, v5.6, v5.5, v5 and v5-fast, where it defaults to 5. pixverse-c1 and every third-party model require it. Accepted values depend on the model — see Model Capabilities. Ignored when template_id is set.

  • quality is optional for the native models v6, v5.6, v5.5, v5 and v5-fast. pixverse-c1 and every third-party model require it. Accepted values depend on the model — see Model Capabilities. kling-4.0 takes 720p or 1080p as the real output resolution. For kling-o3 and kling-v3, quality selects an upstream tier rather than an output resolution — 720p routes to Standard, 1080p to Pro, and 2160p to the 4K tier. PixVerse renders both Standard and Pro at 720p, so only 2160p changes the resolution. When template_id is set, must be one of the template’s qualities (see GET videos/effects); defaults to the first entry if omitted.

  • aspect_ratio is optional. For t2v (no image) it defaults to 16:9. Not accepted for i2v (derived from input image). See Model Capabilities for per-model supported values.

  • auto_sound is optional. Set to true to generate videos with sound or false to explicitly remove the default effect sound.
    Supported values: not specified (default), false, true.

  • sound_effect_prompt is optional, describe the sound eg “the sound of waves hitting the shore”.

  • lip_sync_tts_prompt is optional, enter character lines.
    Maximum length 140 characters.

  • lip_sync_tts_speaker_id is optional, specify desired lipsync voice see GET videos/voices.

  • audio is optional. Supported values: false, true. Both which values are accepted and what happens when you omit the field depend on the model:

    Behavior Models What it means
    Toggle v5.5, v5.6, v6, pixverse-c1, seedance-2.0, seedance-2.0-fast, seedance-2.0-mini, kling-o3, kling-v3, flux-3.0, wan-3.0 true or false accepted, and enables integrated audio generation
    Always on veo-3.1-standard, veo-3.1-fast, happyhorse-1.0 Audio generated automatically; setting false is rejected
    Not supported seedance-2.5, seedance-2.5-flash, seedance-2.5-draft, grok-imagine, grok-imagine-1.5, veo-3.1-lite, minimax-h3, minimax-h3-max, gemini-omni-flash, kling-4.0 Passing any value is rejected

    The Seedance 2.5 models, minimax-h3, minimax-h3-max, gemini-omni-flash and kling-4.0 always generate native audio and accept no audio parameter.

    Omitting audio does not mean off for every model. On the combo models in the Toggle row above — seedance-2.0, seedance-2.0-fast, seedance-2.0-mini, kling-o3, kling-v3, pixverse-c1, flux-3.0 and wan-3.0 — an omitted field is sent upstream as audio: 1, so pass false explicitly if you want it off. That matters on kling-o3 / kling-v3, where audio adds 40% to the cost at 720p and 1080p. flux-3.0 and wan-3.0 charge nothing extra for it. Only the legacy v5.5 / v5.6 / v6 path treats an omitted field as off.

  • multi_shot is optional. v6 only. Set to true to enable multi-shot storytelling — the AI generates videos with multiple camera angles and scene cuts rather than a single continuous shot. Supported values: false (default), true.

  • preview_mode is optional. Only supported for native PixVerse models (v5, v5.5, v5.6, v5-fast, v6, pixverse-c1) — third-party models reject this flag. Set to true to generate a fast preview at lower quality at 20% off credits. Use POST videos/upscale to upscale the preview to full quality. Supported values: false (default), true.

  • seed is optional. Only supported for native PixVerse models (v5, v5.5, v5.6, v5-fast, v6, pixverse-c1) — third-party models reject this flag. Valid range 1…2147483647.

  • off_peak_mode is optional. Set to true to generate videos during low-demand periods at a reduced credit cost. Only supported for native PixVerse models (v5, v5.5, v5.6, v5-fast, v6, pixverse-c1) — third-party models reject this flag. Discount varies by subscription plan: Pro 30% off, Premium 50% off, Ultra unlimited free. Results are usually delivered within 24 hours. Off-Peak generations are not tracked by the scheduler, don’t count toward concurrent-job limits, and the replyUrl webhook is not called — use GET videos to retrieve results.
    Supported values: false (default), true.

  • relax_mode is optional, for third-party models only (PixVerse’s own models reject it). PixVerse discounts third-party video per model and plan, and the discount applies unless you send relax_mode: false, which pays the full price. relax_mode: true costs the same as leaving it out, and PixVerse records the video as made in its Relax Mode. If PixVerse refuses Relax Mode for that model on the account’s plan, relax_mode: true returns 412 and nothing is charged. As of November 2026:

    Plan Discount
    Ultra, Team Ultra minimax-h3 and wan-3.0 free, seedance-2.0-fast and seedance-2.0-mini 90% off, kling-4.0 80% off, gemini-omni-flash 70% off, Veo 3.1 60% off, flux-3.0 and seedance-2.0 50% off, seedance-2.5 and minimax-h3-max 45% off, kling-o3, grok-imagine-1.5 and happyhorse-1.0 40% off, kling-v3, grok-imagine, seedance-2.5-flash and seedance-2.5-draft 20% off
    Premium minimax-h3 and wan-3.0 free, seedance-2.0-fast and seedance-2.0-mini 30% off
    Pro seedance-2.0-fast and seedance-2.0-mini 10% off
  • replyUrl is optional, place here your callback URL. This is the preferred and most optimal way to receive results quickly — the API polls every 10 seconds and will call the provided replyUrl once the PixVerse video is completed or failed. We recommend using sites like webhook.site to test callback URL functionality. Maximum length 1024 characters. Callback body has the same JSON shape as GET /videos/video_id response.

  • replyRef is optional, place here your reference id which will be stored and returned along with this PixVerse video response / result.
    Maximum length 1024 characters.

  • maxJobs is optional, if not specified value from selected accounts/email will be used. It should not exceed the number of concurrent generations supported by your account subscription plan.
    Valid range: 1…8

Input image paths and templates
effect_type Input count Form to use
(no template_id) 0 or 1 first_frame_path (or frame_1_path) — omit for text-to-video
"1" exactly 1 first_frame_path (or frame_1_path)
"2" exactly 2 first_frame_path + last_frame_path (or frame_1_path + frame_2_path)
"3" 2 to 3 frame_1_path … up to frame_3_path
"4" 2 to 4 frame_1_path … up to frame_4_path
"5" 2 to 5 frame_1_path … up to frame_5_path

Never mix first_frame_path/last_frame_path with frame_N_path. In the numbered form, fill slots in order — no frame_3_path without frame_2_path.

When template_id is set, the template controls model, duration, and quality — skip those parameters. Anything you pass for model or duration is ignored, and quality (if set) must be one the template allows. Image templates (template_type: 2) produce a 1-second still — the response carries image_id instead of video_id.

Responses
  • 200 OK

    Use the returned video_id or image_id to retrieve video status and results using GET videos. Locate the video in the response array and check if the field video_status_final is true or video_status_name is COMPLETED. The field url will contain the generated video link.

    If you specify the optional parameter replyUrl, the API will call the provided replyUrl with video progress updates until the video is complete or fails.

    {
        "video_id": "user:<userid>-pixverse:<email>-video:<number>"
    }
    
  • 400 Bad Request

    {
      "error": "<Error message>"
    }
    
  • 401 Unauthorized

    {
      "error": "Unauthorized"
    }
    
  • 412 Insufficient credits

    Insufficient credits. All Credits have been used up. Please upgrade your membership or purchase credits.

    {
      "error": "All Credits have been used up. Please upgrade your membership or purchase credits."
    }
    

    The same code answers relax_mode: true when PixVerse refuses Relax Mode for the model on the account’s plan. Nothing is charged. Leave relax_mode out, or set it to false.

    {
      "error": "relax_mode: true needs a PixVerse plan with Relax Mode for model <model>, and this account's plan does not have it (see the relax_mode table on https://useapi.net/docs/api-pixverse-v2/post-pixverse-videos-create-v4). Leave relax_mode out or set it to false to pay full credits. PixVerse: <message> (400017)"
    }
    
  • 422 Unprocessable Content

    Moderated message.

    {
      "error": "Your prompt has triggered our AI moderator, please re-enter your prompt"
    }
    
  • 429 Too Many Requests

    Wait in a loop for at least 10..30 seconds and retry again.

    There are two possible cases for API response 429:

    1. API query is full and can not accept new videos/create requests. Size of query defined by maxJobs optional parameter.
      {
       "error": 
         "Account <email> is busy executing <maxJobs> tasks."
         "All configured accounts are running at maximum capacity."
      }
      
    2. The API received an HTTP response status 429 from PixVerse. Please refer to your subscription plan for the maximum allowed tasks in the queue.
      {
        "error": "Reached the limit for concurrent generations."
      }
      
  • 596 Pending mod message

    The account has a pending error, and the API does not use it until you add it again with POST accounts/email. You receive an email when this happens. There are three causes.

    PixVerse could not sign the account in, most often because its password was changed. Add the account again with the current password.

    {
      "error": "Your PixVerse account has pending error. Please address this issue at https://useapi.net/docs/api-pixverse-v2/post-pixverse-accounts-email before making any new API calls.",
      "code": 596
    }
    

    Or PixVerse suspended the account. PixVerse suspends accounts that break its content rules and does not say which generation caused it. The first response carries PixVerse’s own details in account_moderation, and later calls return the same error. Add the account again after reinstatement_at. To ask PixVerse to lift the suspension earlier, write to the support_email it gives.

    {
      "error": "PixVerse suspended account [email protected] for 30 days, from 2026-10-16 09:26 UTC until 2026-11-15 09:26 UTC. PixVerse suspends accounts that break its content rules and does not say which generation caused it. Add the account again at https://useapi.net/docs/api-pixverse-v2/post-pixverse-accounts-email after 2026-11-15 09:26 UTC. To ask PixVerse to lift it earlier, write to [email protected].",
      "code": 596,
      "account_moderation": {
        "ban_level": "suspend_30d",
        "action": "temporary_suspend",
        "duration_days": 30,
        "suspended_at": "2026-10-16 09:26:25 (UTC)",
        "reinstatement_at": "2026-11-15 09:26:25 (UTC)",
        "support_email": "[email protected]"
      }
    }
    

    Or PixVerse banned the account for violating its community guidelines. A ban is permanent unless PixVerse accepts an appeal, and the error quotes PixVerse’s own message, which says how to appeal. Remove the account with DELETE accounts/email, or add it again only if PixVerse lifts the ban.

    {
      "error": "PixVerse banned account [email protected] for violating its community guidelines (400024). A ban is permanent unless PixVerse accepts an appeal. PixVerse says: \"Your account has been banned for violating community guidelines. If you wish to appeal, please contact us via ...\" Remove it with DELETE /v2/pixverse/accounts/[email protected], or add it again (https://useapi.net/docs/api-pixverse-v2/post-pixverse-accounts-email) only if PixVerse lifts the ban.",
      "code": 596
    }
    

    If every account you have is in this state, a request without email returns 596 as well.

Model

The new video’s video_id to poll with GET videos/video_id, or an image_id when an image effect template is used.

The new video job, field by field
{ // TypeScript, all fields are optional
    video_id: string
    image_id: string // When image template_id is used (template_type: 2)
    error: string
}
Examples
  • curl -H "Accept: application/json" \
         -H "Content-Type: application/json" \
         -H "Authorization: Bearer …" \
         -X POST "https://api.useapi.net/v2/pixverse/videos/create" \
         -d '{"prompt": "…"}'
    
  • const prompt = "text prompt";      
    const apiUrl = `https://api.useapi.net/v2/pixverse/videos/create`; 
    const token = "API token";
    const data = { 
      method: 'POST',
      headers: {
        'Authorization': `Bearer ${token}`,
        'Content-Type': 'application/json' }
    };
    data.body = JSON.stringify({ 
      prompt
    });
    const response = await fetch(apiUrl, data);
    const result = await response.json();
    console.log("response", {response, result});
    
  • import requests
    prompt = "text prompt"      
    apiUrl = f"https://api.useapi.net/v2/pixverse/videos/create" 
    token = "API token"
    headers = {
        "Content-Type": "application/json", 
        "Authorization" : f"Bearer {token}"
    }
    body = {
        "prompt": f"{prompt}"
    }
    response = requests.post(apiUrl, headers=headers, json=body)
    print(response, response.json())
    
Try It