kling-2.5-turbo API

Use the exact model ID kling-2.5-turbo. The model field must match this page exactly.

Sample outputkling-2.5-turboPOST /v1/videos5.0s

Parameters: duration=5resolution=1080pratio=16:9

Prompt: One continuous take, no cuts. A night market grill under plastic awnings, skewers over coals. A cook in a lacquer-red jacket fans the fire once and the sparks refuse to die: they climb, gather and turn into a flock of small orange birds that wheels above the stalls and pours down the length of the street. The camera starts tight on the coals, pulls back and rises with the flock over the awnings. One hard warm key from the grill itself, cold blue street beyond. Real weight and inertia, smoke and heat shimmer, no text.

Request that produced this sample

{
  "model": "kling-2.5-turbo",
  "prompt": "One continuous take, no cuts. A night market grill under plastic awnings, skewers over coals. A cook in a lacquer-red jacket fans the fire once and the sparks refuse to die: they climb, gather and turn into a flock of small orange birds that wheels above the stalls and pours down the length of the street. The camera starts tight on the coals, pulls back and rises with the flock over the awnings. One hard warm key from the grill itself, cold blue street beyond. Real weight and inertia, smoke and heat shimmer, no text.",
  "seconds": "5",
  "duration": 5,
  "resolution": "1080p",
  "ratio": "16:9",
  "aspect_ratio": "16:9"
}

Authentication and endpoint

Use a Modelflare API key with https://modelflare.dev/v1. The gateway entry point is POST /v1/videos.

HTTP

Authorization: Bearer YOUR_MODELFLARE_API_KEY

Create a task

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-2.5-turbo",
    "prompt": "A white cat runs through a neon-lit street in the rain, cinematic tracking shot",
    "duration": "5", "mode": "std"
  }'

Poll and download

Save the task ID. Poll GET /v1/videos/{task_id} and download with GET /v1/videos/{task_id}/content. Result URLs may expire, so transfer the file promptly.

bash

curl https://modelflare.dev/v1/videos/TASK_ID \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY"

Request notes

Kling uses family-specific model_name, prompt, mode, duration, image_list, or contents / settings fields; native JSON is preserved and forwarded.

Request parameters

Kling Legacy uses model_name with the text2video / image2video request structures. Check the model’s official page and pricing page for mode, resolution, and audio lanes.

Field	Required	Notes
model_name	Yes	kling-2.5-turbo
prompt	Conditional	Required for text-to-video; combine with images for image-to-video
image	Conditional	First-frame image URL or Base64
image_tail	No	Optional end-frame image
video_url	Conditional	Reference video for Kling 3.0 motion control
image_list	No	Image list for Omni/O1 and multimodal workflows
negative_prompt	No	Negative prompt
mode	No	std / pro / 4k (model-dependent)
duration	No	5 / 10（字符串）
multi_shot	No	Enable multi-shot storyboarding
sound	No	Generate synchronized sound where supported
camera_control	No	Camera control where supported

Input and output limits

Kling 2.5 Turbo uses the Legacy API with fixed 5/10-second durations and 720p/1080p. It supports text-to-video and single-first-frame image-to-video, but not native audio, voices, multi-shot, motion brush, or camera control.

Documented workflow examples

Legacy models select model_name, first/end-frame, or motion-control fields by workflow; fixed duration and audio limits follow this page’s table.

bash

curl https://modelflare.dev/v1/videos \
  -H "Authorization: Bearer YOUR_MODELFLARE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model_name": "kling-2.5-turbo", "prompt": "一只狗在海边奔跑",
    "duration": "5", "mode": "pro", "aspect_ratio": "16:9", "sound": "off"
  }'

Errors and failed tasks

Invalid model parameters return a 4xx with a request ID. An asynchronous task can also enter failed after creation succeeds; use error_code and error_message from the poll response as the final task reason. Do not retry the same request with a different JSON shape.

Supported scope

This page covers Modelflare model generation and editing calls. Search or map enrichment, voice management, and element-library management are resource APIs outside this public model-call surface and are not required request fields.

Pricing and billing

This model uses per-second video billing. See the model pricing page for the current customer price, reference list price, and complete specification.

Note

This page documents Modelflare’s public interface; the fields and limits shown here are the current contract.