Skip to main content

Documentation Index

Fetch the complete documentation index at: https://docs.lemondata.cc/llms.txt

Use this file to discover all available pages before exploring further.

​
Overview

For coding agents, discover the current recommended video shortlist first with GET /v1/models?recommended_for=video, then send the selected model explicitly to this endpoint. Video generation is asynchronous. You submit a request, receive a canonical async task ID and poll_url, then poll for the result.

​
Polling behavior

For the most reliable polling behavior, follow the exact poll_url returned by the create request. If a create response returns poll_url, call that exact URL. When it points to /v1/tasks/{id}, treat that as the canonical fixed status endpoint. The async task identifier may surface as id or task_id depending on the adapter. Treat them as the same task identity.

​
Model and media behavior

Audio output is model-dependent. In LemonData, Veo 3 family requests default to audio-on when output_audio is omitted. When a model supports audio control, use output_audio to explicitly toggle it. The camelCase alias outputAudio is also accepted for compatibility. For production integrations, prefer publicly reachable https URLs for images, videos, and audio. Inline data: URLs remain supported for compatible models, but large base64 payloads are harder to retry, inspect, and debug.

​
Request Body

​
model
string
default:"sora-2"
Video model ID. API default is sora-2. See the Video Generation Guide for the current public model matrix and supported capabilities.
​
prompt
string
required
Text description of the video to generate. Required for most public video models.
​
operation
string
Video operation to run. Supported contract values include text-to-video, image-to-video, reference-to-video, start-end-to-video, video-to-video, video-extension, audio-to-video, and motion-control. LemonData can infer the operation from the supplied inputs, but explicit operation is recommended for production reliability.
​
image_url
string
Publicly accessible URL of the starting image for image-to-video generation. For best cross-model compatibility, prefer image_url.
​
image
string
Inline image as a data URL (for example, data:image/jpeg;base64,...). Supported by compatible models, but image_url provides the broadest compatibility across public video models.
​
reference_images
array
Reference image inputs for models that support dedicated reference conditioning. The supported count is model-dependent. For seedance-2.0 and seedance-2.0-fast, LemonData currently supports up to 9 reference images plus up to 3 reference videos and 3 reference audios. Public https URLs are recommended; compatible models also accept inline data: URLs.
​
reference_image_type
string
Optional reference role for models that distinguish between asset and style references.
​
video_url
string
Publicly accessible URL of the source video. Required for video-to-video style flows and for motion-control models that combine a subject image with a motion reference video.
​
video_urls
array
Additional reference video inputs for models that support multimodal reference conditioning. The supported count is model-dependent. For seedance-2.0 and seedance-2.0-fast, LemonData currently supports up to 3 reference videos.
​
audio_url
string
Publicly accessible audio URL for models that support audio-to-video.
​
audio_urls
array
Additional reference audio inputs for models that support multimodal reference conditioning. The supported count is model-dependent. For seedance-2.0 and seedance-2.0-fast, LemonData currently supports up to 3 reference audios.
​
task_id
string
Provider-specific task identifier used by some continuation, extension, or derivative flows.
​
extend_at
integer
Model-specific extension start offset used by some video-extension flows.
​
extend_times
string
Model-specific extension multiplier or repeat count used by some video-extension flows.
​
duration
integer
Generated output video duration in seconds (model-dependent). This field controls output length, not the duration of reference video inputs.
​
aspect_ratio
string
Aspect ratio (for example, 16:9, 9:16, or 1:1).
​
resolution
string
Model-dependent output resolution (for example, 720p, 1080p, or 4k).
​
output_audio
boolean
Model-dependent audio output toggle. In LemonData, Veo 3 family requests default to true when this field is omitted. Other public video models follow their governed default behavior. The camelCase alias outputAudio is accepted for compatibility.
​
fps
integer
Frames per second (1-120) for models that expose FPS control.
​
negative_prompt
string
What to avoid in the generated video.
​
seed
integer
Random seed for reproducible generation.
​
cfg_scale
number
Prompt adherence strength (0-20) for models that expose CFG-style control.
​
motion_strength
number
Motion intensity (0-1) for models that expose it.
​
start_image
string
URL or compatible image input for the first frame in start-end-to-video.
​
end_image
string
URL or compatible image input for the last frame in start-end-to-video.
​
size
string
Model-specific size tier used by some OpenAI-compatible video models.
​
watermark
boolean
Optional watermark toggle for models that expose it.
​
effect_type
string
Model-specific effect selector for specialized editing flows.
​
user
string
A unique identifier for the end-user.

​
Compatibility Notes

  • Canonical public fields are snake_case: reference_images, reference_image_type, and output_audio.
  • For compatibility, LemonData also accepts the camelCase aliases referenceImages, referenceImageType, and outputAudio.
  • If operation is omitted, LemonData infers it from the supplied inputs. For production traffic, explicit operation is still recommended.

​
Media Input Best Practices

  • Prefer publicly reachable https URLs over inline base64 for image_url, reference_images, video_url, and audio_url.
  • Avoid mixing inline base64 and remote URLs in the same request when possible; using one representation per request is easier to reason about and debug.
  • If you use signed URLs, keep them valid long enough to cover retries and asynchronous task creation.

​
Response

​
id
string
Canonical async task identifier. Treat this as the same identity as task_id when both are present.
​
task_id
string
Canonical async task identifier for polling. This is the same task identity used by async status endpoints.
​
poll_url
string
Preferred polling URL for this task. Use this exact path when checking status.
​
billing_transaction_id
string
LemonData billing transaction ID when settlement already completed. This is the dashboard/accounting transaction identifier and is separate from the async id / task_id.
​
status
string
Initial status: pending.
​
created
integer
Unix timestamp when the task was created.
​
model
string
Model used.
​
video_url
string
Direct video URL when the result is already available.
​
video
object
Single video payload with url, duration, width, and height when available.
​
videos
array
Multiple video payloads when the provider returns more than one output.
​
error
string
Error message or structured error object when the task fails.
curl -X POST "https://api.lemondata.cc/v1/videos/generations" \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sora-2",
    "prompt": "A cat walking through a garden, cinematic lighting",
    "operation": "text-to-video",
    "duration": 4,
    "aspect_ratio": "16:9"
  }'

{
  "id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "task_id": "ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "poll_url": "/v1/tasks/ldtask_aaaaaaaaaaaaaaaaaaaaaaaaaaaaaaaa",
  "status": "pending",
  "model": "sora-2",
  "created": 1706000000
}

​
Image to Video

response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "hailuo-2.3-standard",
        "prompt": "The scene begins from the provided image and adds gentle natural motion.",
        "operation": "image-to-video",
        "image_url": "https://example.com/image.jpg",
        "duration": 6,
        "aspect_ratio": "16:9"
    }
)

​
Reference to Video

Use operation=reference-to-video when the model supports dedicated reference conditioning. In LemonData’s public contract, image references use reference_images, while multimodal reference videos and audios use video_urls and audio_urls. For seedance-2.0 and seedance-2.0-fast, LemonData currently supports up to 9 reference images plus up to 3 reference videos and 3 reference audios. duration controls generated output length only; it does not set a separate limit for reference video input duration. 
response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "veo3.1",
        "prompt": "Keep the same subject identity, palette, and framing while adding subtle natural motion.",
        "operation": "reference-to-video",
        "reference_images": [
            "https://example.com/ref-a.jpg",
            "https://example.com/ref-b.jpg"
        ],
        "reference_image_type": "asset",
        "duration": 8,
        "resolution": "720p",
        "aspect_ratio": "9:16"
    }
)

​
Keyframe Control

Use start_image and end_image to control the first and last frames: 
response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "viduq2-pro",
        "prompt": "Smooth transition from day to night",
        "operation": "start-end-to-video",
        "start_image": "https://example.com/day.jpg",
        "end_image": "https://example.com/night.jpg",
        "duration": 5,
        "resolution": "720p",
        "aspect_ratio": "16:9"
    }
)

​
Video to Video

Use operation=video-to-video when the model accepts an existing video as the primary input. 
response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "topaz-video-upscale",
        "operation": "video-to-video",
        "video_url": "https://example.com/source.mp4",
        "prompt": "Upscale the clip while preserving the original motion.",
        "resolution": "1080p"
    }
)

​
Motion Control

Use operation=motion-control when the model expects both a subject image and a motion reference video. LemonData maps the public image_url + video_url request shape to the upstream motion-control contract. 
response = requests.post(
    "https://api.lemondata.cc/v1/videos/generations",
    headers={"Authorization": "Bearer sk-your-api-key"},
    json={
        "model": "kling-3.0-motion-control",
        "operation": "motion-control",
        "prompt": "Keep the subject identity stable while following the motion reference.",
        "image_url": "https://example.com/subject.png",
        "video_url": "https://example.com/motion.mp4",
        "resolution": "720p"
    }
)

​
Audio-to-Video and Video Extension Availability

LemonData’s public contract accepts audio-to-video and video-extension for model-specific flows, but the current generally enabled public video model list in this docs build does not include a broad public model that advertises either capability. Use the Models API or the Models page to confirm current availability before integrating those operations.

​
Currently Enabled Public Video Models

This list is aligned with the current enabled public video model inventory in this docs build. For the freshest state, query the Models API.

​
OpenAI

ModelPublic operations
sora-2Text-to-video, image-to-video
sora-2-proText-to-video, image-to-video
sora-2-pro-storyboardImage-to-video

​
Kuaishou

ModelPublic operations
kling-3.0-motion-controlMotion control
kling-3.0-videoText-to-video, image-to-video, start-end-to-video
kling-v2.5-turbo-proText-to-video, image-to-video, start-end-to-video
kling-v2.5-turbo-stdText-to-video, image-to-video
kling-v2.6-proText-to-video, image-to-video, start-end-to-video
kling-v2.6-stdText-to-video, image-to-video
kling-v3.0-proText-to-video, image-to-video, start-end-to-video
kling-v3.0-stdText-to-video, image-to-video, start-end-to-video
kling-video-o1-proText-to-video, image-to-video, reference-to-video, start-end-to-video, video-to-video
kling-video-o1-stdText-to-video, image-to-video, reference-to-video, start-end-to-video, video-to-video

​
Google

ModelPublic operations
veo3Text-to-video, image-to-video
veo3-fastText-to-video, image-to-video
veo3-proText-to-video, image-to-video
veo3.1Text-to-video, image-to-video, reference-to-video, start-end-to-video
veo3.1-fastText-to-video, image-to-video, reference-to-video, start-end-to-video
veo3.1-proText-to-video, image-to-video, start-end-to-video

​
ByteDance

ModelPublic operations
seedance-1.5-proText-to-video, image-to-video

​
MiniMax

ModelPublic operations
hailuo-2.3-fastImage-to-video
hailuo-2.3-proText-to-video, image-to-video
hailuo-2.3-standardText-to-video, image-to-video

​
Alibaba

ModelPublic operations
wan-2.2-plusText-to-video, image-to-video
wan-2.5Text-to-video, image-to-video
wan-2.6Text-to-video, image-to-video, reference-to-video

​
Shengshu

ModelPublic operations
viduq2Text-to-video, reference-to-video
viduq2-proImage-to-video, reference-to-video, start-end-to-video
viduq2-pro-fastImage-to-video, start-end-to-video
viduq2-turboImage-to-video, start-end-to-video
viduq3-proText-to-video, image-to-video, start-end-to-video
viduq3-turboText-to-video, image-to-video, start-end-to-video

​
xAI

ModelPublic operations
grok-imagine-image-to-videoImage-to-video
grok-imagine-text-to-videoText-to-video
grok-imagine-upscaleVideo-to-video

​
Other

ModelPublic operations
topaz-video-upscaleVideo-to-video