Kling AI Video Generator API documentation

Generate videos with Kling AI Video Generator (Kuaishou Kling AI). Supports both text and image input modes.

Endpoints

Contract item	Value
Capability	`kling-ai-video-generator`
Submit	`POST https://vidmage.ai/api/v1/kling-ai-video-generator/submit`
Query	`POST https://vidmage.ai/api/v1/kling-ai-video-generator/query`
Task identifier	`taskId`
Result field	`videoUrl`

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Product guide: Kling API

Parameters and input rules

Field	Type	Required	Default	Meaning and limits
`prompt`	`string`	Yes	Not specified	Text prompt describing the video to generate (max 2500 chars). Minimum characters: `1` Maximum characters: `2500`
`imageUrl`	`string`	No	Not specified	Optional input image URL. When provided, the task runs in image-to-video mode. In that mode, output ratio is inferred from the input image.
`lastFrameUrl`	`string`	No	Not specified	Optional public URL for the final frame in image-to-video mode.
`duration`	`string`	No	`"5"`	Video duration in seconds. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`
`aspectRatio`	`string`	No	`"16:9"`	Output aspect ratio for modes that expose a ratio parameter. Ignored when imageUrl selects a mode whose ratio is inferred from the input image. Values: `"16:9"`, `"9:16"`, `"1:1"`
`sound`	`boolean`	No	`true`	Generate synchronized audio along with the video. Enabling sound adds a per-second credit surcharge.
`negativePrompt`	`string`	No	`"Flickering, blur, distorted limbs, watermark, low resolution."`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500`
`cfgScale`	`number`	No	`0.5`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1`
`multiShot`	`boolean`	No	`false`	Generate a video composed of multiple shots.
`shotType`	`string`	No	`"customize"`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"`
`multiPrompt`	`string[]`	No	`[]`	Additional prompts for complex multi-shot compositions. Maximum items: `6`
`elementList`	`string[]`	No	`[]`	Element references to preserve across the generated shot. Maximum items: `3`

text to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–2500 characters.
`duration`	JSON string. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`. Default: `5`.
`aspectRatio`	Values: `"16:9"`, `"9:16"`, `"1:1"`. Default: `16:9`.
`resolution`	Not used in this mode.
`sound`	Boolean. Default: `true`.
`negativePrompt`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500` Default: `"Flickering, blur, distorted limbs, watermark, low resolution."`
`cfgScale`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1` Default: `0.5`
`multiShot`	Generate a video composed of multiple shots. Default: `false`
`shotType`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"` Default: `"customize"`
`multiPrompt`	Additional prompts for complex multi-shot compositions. Maximum items: `6` Default: `[]`

image to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–2500 characters.
`duration`	JSON string. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`. Default: `5`.
`aspectRatio`	Not used in this mode.
`resolution`	Not used in this mode.
`sound`	Boolean. Default: `true`.
`imageUrl`	Formats: jpg, png.
`lastFrameUrl`	Optional final-frame image.
`negativePrompt`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500`
`cfgScale`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1` Default: `0.8`
`multiShot`	Generate a video composed of multiple shots. Default: `false`
`shotType`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"` Default: `"customize"`
`multiPrompt`	Additional prompts for complex multi-shot compositions. Maximum items: `6` Default: `[]`
`elementList`	Element references to preserve across the generated shot. Maximum items: `3` Default: `[]`

Example request

{
  "prompt": "A cinematic tracking shot follows a cyclist through a quiet forest as morning fog drifts between the trees",
  "duration": "5",
  "aspectRatio": "16:9",
  "sound": true,
  "negativePrompt": "Flickering, blur, distorted limbs, watermark, low resolution.",
  "cfgScale": 0.5,
  "multiShot": false,
  "shotType": "customize"
}

# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/kling-ai-video-generator/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A cinematic tracking shot follows a cyclist through a quiet forest as morning fog drifts between the trees","duration":"5","aspectRatio":"16:9","sound":true,"negativePrompt":"Flickering, blur, distorted limbs, watermark, low resolution.","cfgScale":0.5,"multiShot":false,"shotType":"customize"}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the generated video. Read videoUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/kling-ai-video-generator/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "videoUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Credits

Component / option	Rate	Minimum
Base rate	20 credits / second	—

Base charge = duration × the selected resolution rate.

Sound adds 5 credits per second before option multipliers.

Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.

Integration guides

Authentication · File uploads · Task lifecycle · Error recovery · MCP

Kling AI Video Generator API documentation

Generate videos with Kling AI Video Generator (Kuaishou Kling AI). Supports both text and image input modes.

Endpoints

Contract item	Value
Capability	`kling-ai-video-generator`
Submit	`POST https://vidmage.ai/api/v1/kling-ai-video-generator/submit`
Query	`POST https://vidmage.ai/api/v1/kling-ai-video-generator/query`
Task identifier	`taskId`
Result field	`videoUrl`

Authenticate with Authorization: Bearer YOUR_API_KEY. Save the task identifier and query the same capability. Use a stable Idempotency-Key for submission retries.

Product guide: Kling API

Parameters and input rules

Field	Type	Required	Default	Meaning and limits
`prompt`	`string`	Yes	Not specified	Text prompt describing the video to generate (max 2500 chars). Minimum characters: `1` Maximum characters: `2500`
`imageUrl`	`string`	No	Not specified	Optional input image URL. When provided, the task runs in image-to-video mode. In that mode, output ratio is inferred from the input image.
`lastFrameUrl`	`string`	No	Not specified	Optional public URL for the final frame in image-to-video mode.
`duration`	`string`	No	`"5"`	Video duration in seconds. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`
`aspectRatio`	`string`	No	`"16:9"`	Output aspect ratio for modes that expose a ratio parameter. Ignored when imageUrl selects a mode whose ratio is inferred from the input image. Values: `"16:9"`, `"9:16"`, `"1:1"`
`sound`	`boolean`	No	`true`	Generate synchronized audio along with the video. Enabling sound adds a per-second credit surcharge.
`negativePrompt`	`string`	No	`"Flickering, blur, distorted limbs, watermark, low resolution."`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500`
`cfgScale`	`number`	No	`0.5`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1`
`multiShot`	`boolean`	No	`false`	Generate a video composed of multiple shots.
`shotType`	`string`	No	`"customize"`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"`
`multiPrompt`	`string[]`	No	`[]`	Additional prompts for complex multi-shot compositions. Maximum items: `6`
`elementList`	`string[]`	No	`[]`	Element references to preserve across the generated shot. Maximum items: `3`

text to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–2500 characters.
`duration`	JSON string. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`. Default: `5`.
`aspectRatio`	Values: `"16:9"`, `"9:16"`, `"1:1"`. Default: `16:9`.
`resolution`	Not used in this mode.
`sound`	Boolean. Default: `true`.
`negativePrompt`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500` Default: `"Flickering, blur, distorted limbs, watermark, low resolution."`
`cfgScale`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1` Default: `0.5`
`multiShot`	Generate a video composed of multiple shots. Default: `false`
`shotType`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"` Default: `"customize"`
`multiPrompt`	Additional prompts for complex multi-shot compositions. Maximum items: `6` Default: `[]`

image to video

These are public VidMage field names. The server maps them to provider fields. Input media selects the mode; use its limits together with the parameter table.

Control	Mode-specific rule
`prompt`	Required; 1–2500 characters.
`duration`	JSON string. Values: `"3"`, `"4"`, `"5"`, `"6"`, `"7"`, `"8"`, `"9"`, `"10"`, `"11"`, `"12"`, `"13"`, `"14"`, `"15"`. Default: `5`.
`aspectRatio`	Not used in this mode.
`resolution`	Not used in this mode.
`sound`	Boolean. Default: `true`.
`imageUrl`	Formats: jpg, png.
`lastFrameUrl`	Optional final-frame image.
`negativePrompt`	Describe unwanted video content or artifacts. Minimum characters: `0` Maximum characters: `2500`
`cfgScale`	Prompt guidance strength. Minimum: `0` Maximum: `1` Multiple of: `0.1` Default: `0.8`
`multiShot`	Generate a video composed of multiple shots. Default: `false`
`shotType`	Use custom or automatically planned shot structure. Values: `"customize"`, `"intelligence"` Default: `"customize"`
`multiPrompt`	Additional prompts for complex multi-shot compositions. Maximum items: `6` Default: `[]`
`elementList`	Element references to preserve across the generated shot. Maximum items: `3` Default: `[]`

Example request

{
  "prompt": "A cinematic tracking shot follows a cyclist through a quiet forest as morning fog drifts between the trees",
  "duration": "5",
  "aspectRatio": "16:9",
  "sound": true,
  "negativePrompt": "Flickering, blur, distorted limbs, watermark, low resolution.",
  "cfgScale": 0.5,
  "multiShot": false,
  "shotType": "customize"
}

# Set VIDMAGE_IDEMPOTENCY_KEY to a unique value for this task; preserve it for transport retries.
curl -X POST "https://vidmage.ai/api/v1/kling-ai-video-generator/submit" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Idempotency-Key: ${VIDMAGE_IDEMPOTENCY_KEY}" \
  -H "Content-Type: application/json" \
  -d '{"prompt":"A cinematic tracking shot follows a cyclist through a quiet forest as morning fog drifts between the trees","duration":"5","aspectRatio":"16:9","sound":true,"negativePrompt":"Flickering, blur, distorted limbs, watermark, low resolution.","cfgScale":0.5,"multiShot":false,"shotType":"customize"}'
# -> { "success": true, "taskId": "...", "creditsConsumed": ... }

Task results and recovery

URL of the generated video. Read videoUrl from the completed query response. Preserve taskId while the task is running.

curl -X POST "https://vidmage.ai/api/v1/kling-ai-video-generator/query" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{ "taskId": "TASK_ID_FROM_SUBMIT" }'
# -> { "success": true, "data": { "status": "...", "videoUrl": "https://..." } }

Submission and task queries report the available task and usage information. A timeout is not a confirmed failure. Recover the existing task instead of resubmitting.

For face selection and error recovery, follow Task lifecycle. MCP uses the normalized taskId argument in get_task_result, including capabilities whose REST identifier is requestId.

Credits

Component / option	Rate	Minimum
Base rate	20 credits / second	—

Base charge = duration × the selected resolution rate.

Sound adds 5 credits per second before option multipliers.

Use the Playground or the MCP credit estimator for your exact inputs. Credits and billing.

Integration guides

Authentication · File uploads · Task lifecycle · Error recovery · MCP