PixVerse V6 Text To Video

From 30 credits/sec
ae_pixverse_v6_text_to_video

Create styled video clips from text prompts, with controls for duration, aspect ratio, resolution, audio, negative prompts, and multi-clip camera changes.

Video
From 30 credits/sec

Pricing

From 30 credits/sec
ResolutionGenerate audio: Disabled / Not specifiedGenerate audio: Enabled
360p30 credits/second42 credits/second
540p42 credits/second54 credits/second
720p / Not specified54 credits/second72 credits/second
1080p108 credits/second138 credits/second

When duration is omitted, billing is based on five seconds. Starting price applies to Generate audio: Disabled, Resolution: 360p.

Parameters

Optional parameters use the platform defaults when omitted.

ParameterTypeRequiredDescriptionDefault
request_bodyobjectYesNo parameter description.—
request_body.seedinteger | unknownNo The same seed and the same prompt given to the same version of the model will output the same video every time. —
request_body.stylestring | unknownNoThe style of the generated video—
request_body.promptstringYesNo parameter description.—
request_body.durationintegerNoThe duration of the generated video in seconds. v6 supports values from 1 to 15 seconds5
request_body.resolutionenum (360p | 540p | 720p | 1080p)NoThe resolution of the generated video720p
request_body.aspect_ratioenum (16:9 | 4:3 | 1:1 | 3:4 | 9:16 | 2:3 | 3:2 | 21:9)NoThe aspect ratio of the generated video16:9
request_body.thinking_typestring | unknownNoPrompt optimization mode: 'enabled' to optimize, 'disabled' to turn off, 'auto' for model decision—
request_body.negative_promptstringNoNegative prompt to be used for the generation""
request_body.generate_audio_switchbooleanNoEnable audio generation (BGM, SFX, dialogue)false
request_body.generate_multi_clip_switchbooleanNoEnable multi-clip generation with dynamic camera changesfalse

Invocation example

Copy the request and explore its response example.

POST/agent-api/v1/tool/executeX-Api-Key

Submit first, then query with the returned task_id until the task completes.

Request coderequest.sh
curl --request POST \
  --url 'https://agentearth.ai/agent-api/v1/tool/execute?tool_name=ae_pixverse_v6_text_to_video' \
  --header "X-Api-Key: $AGENTEARTH_API_KEY" \
  --header 'Content-Type: application/json' \
  --data-raw '{
  "params": {
    "request_body": {
      "aspect_ratio": "9:16",
      "duration": 8,
      "generate_audio_switch": false,
      "negative_prompt": "blurry, low quality, low resolution, pixelated, noisy, grainy, out of focus, poorly lit, poorly exposed, poorly composed, poorly framed, poorly cropped, poorly color corrected, poorly color graded, text, watermark, subtitles, cartoon, deformed",
      "prompt": "3D 微观特写视角,大量发光白色原子粒子撞击上方水平放置的晶体基片表面,一部分粒子反弹飞走,一部分吸附在基片表面,吸附粒子在表面缓慢游动、互相碰撞抱团,形成微小的高亮原子簇团,深色背景,科技感光晕,镜头缓慢横移,画面精致细腻",
      "resolution": "720p",
      "style": "3d_animation"
    }
  }
}'
Response exampleresponse.json
JSON
{
  "description": "task accepted; poll the result via query_tool with this task_id",
  "query_tool": "ae_get_result",
  "status": "created",
  "task_id": "1dd71f6f-79d6-4610-8bd6-7388b8a89a74"
}

Guides using this tool

See how this tool fits into real workflows