Kling 3.0 API 调用参考
4K 视频、多镜头剪切和动作控制
用一个 PopNow API 密钥，就能在自己的代码里调用 Kling 3.0。下面列出要填的调用名、这个型号接受的每个输入字段、每次请求花多少积分，以及一段可以直接粘进终端运行的请求。
参数说明直接取自型号的输入 schema，暂时只有英文。
一览
- 出品方
- Kuaishou
- 产出
- 视频
- 起价
- 10.08 积分 每秒成片 ($0.1008)
- 一般耗时
- 约 400 秒
1 积分 = 0.01 美元。任务受理时先冻结可能的最高费用，完成后按实际用量结算、向上取整到整积分，多冻的退回；失败的任务不扣积分。想在运行前知道确切数字，先调 POST /api/v1/jobs/quote。
生成视频
kling/3.0/text-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 720p | 10.08 | $0.1008 |
generate_audio = false, resolution = 1080p | 13.44 | $0.1344 |
generate_audio = true, resolution = 720p | 15.12 | $0.1512 |
generate_audio = true, resolution = 1080p | 20.16 | $0.2016 |
generate_audio = false, resolution = 4k | 50.4 | $0.504 |
generate_audio = true, resolution = 4k | 50.4 | $0.504 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | 最多 2500 个字符 | Describe the scene, the action and the camera. With sound on, add dialogue in quotes and the sounds you want. |
negative_prompt可选 | string | — | 最多 2500 个字符 | What to keep out of the clip: objects, looks or motion you do not want. |
aspect_ratio可选 | string | 16:9 | 16:9, 9:16, 1:1 | Output aspect ratio. |
resolution可选 | string | 720p | 720p, 1080p, 4k | Output resolution. Higher tiers cost more per second. |
generate_audio可选 | boolean | false | — | Generate a native soundtrack (voices, effects, ambience) with the picture. Audio costs more per second. |
duration_seconds可选 | integer | 5 | 3 到 15 | Output length in whole seconds, from 3 to 15. Billed per second. |
shot_type可选 | string | single | single, multi, customize | single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt. |
multi_prompt可选 | array<object> | — | 最多 6 项 | Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds. |
guidance_scale可选 | number | 0.5 | 0 到 1 | How closely the clip follows the prompt, from 0 to 1. Higher sticks to the prompt more; lower gives the model more freedom. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "kling/3.0/text-to-video",
"input": {
"prompt": "A paper boat drifts down a rain-soaked street at dusk, neon signs reflecting in the water, slow tracking shot at ground level",
"duration_seconds": 5,
"generate_audio": false,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"图生视频
kling/3.0/image-to-video
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
generate_audio = false, resolution = 720p | 10.08 | $0.1008 |
generate_audio = false, resolution = 1080p | 13.44 | $0.1344 |
generate_audio = true, resolution = 720p | 15.12 | $0.1512 |
generate_audio = true, resolution = 1080p | 20.16 | $0.2016 |
generate_audio = false, resolution = 4k | 50.4 | $0.504 |
generate_audio = true, resolution = 4k | 50.4 | $0.504 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
prompt必填 | string | — | 最多 2500 个字符 | Describe what happens after the opening frame: the action, the camera and, with sound on, the sounds. |
image_url必填 | string (uri) | — | — | Opening frame. The clip starts from this image. |
negative_prompt可选 | string | — | 最多 2500 个字符 | What to keep out of the clip: objects, looks or motion you do not want. |
last_image_url可选 | string (uri) | — | — | Optional closing frame the clip should end on. |
resolution可选 | string | 720p | 720p, 1080p, 4k | Output resolution. Higher tiers cost more per second. |
generate_audio可选 | boolean | false | — | Generate a native soundtrack (voices, effects, ambience) with the picture. Audio costs more per second. |
duration_seconds可选 | integer | 5 | 3 到 15 | Output length in whole seconds, from 3 to 15. Billed per second. |
shot_type可选 | string | single | single, multi, customize | single keeps one continuous shot; multi lets the model cut the prompt into several shots on its own; customize follows the shot list you give in multi_prompt. |
multi_prompt可选 | array<object> | — | 最多 6 项 | Shot list for shot_type customize: one entry per shot, in order, each with its own prompt and length in seconds. The lengths must add up to duration_seconds. |
guidance_scale可选 | number | 0.5 | 0 到 1 | How closely the clip follows the prompt, from 0 to 1. Higher sticks to the prompt more; lower gives the model more freedom. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
示例里的 image_url 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "kling/3.0/image-to-video",
"input": {
"prompt": "He lands softly on the rooftop, laughs and turns toward the camera while the balloons sway in the evening breeze; slow push-in",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"duration_seconds": 5,
"generate_audio": false,
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"动作控制
kling/3.0/character-animation
价格
| 选项 | 积分 (每秒成片) | 美元 |
|---|---|---|
720p | 15.12 | $0.1512 |
1080p | 20.16 | $0.2016 |
参数
| 字段 | 类型 | 默认值 | 取值范围 | 作用 |
|---|---|---|---|---|
image_url必填 | string (uri) | — | — | The character to animate: one clear, full or half-body picture of the person. |
video_url必填 | string (uri) | — | — | Driving clip, 3 to 30 seconds: the moves, expressions and gestures to copy. The result is as long as this clip. |
prompt可选 | string | — | 最多 2500 个字符 | Optional notes on the result: the setting, the look, anything the driving clip does not show. |
negative_prompt可选 | string | — | 最多 2500 个字符 | What to keep out of the result: objects, looks or motion you do not want. |
resolution可选 | string | 720p | 720p, 1080p | Output resolution. Higher tiers cost more per second. |
keep_original_audio可选 | boolean | true | — | Keep the driving clip's own sound in the result. |
character_orientation可选 | string | video | video, image | Which way the character faces: video follows the person in the driving clip, image follows the person in the photo. With image the driving clip may be at most 10 seconds. |
shot_type可选 | string | customize | customize, intelligent | How the shots are planned: customize keeps to your inputs, intelligent lets the model plan the shots itself. |
请求示例
这段请求原样就能运行，没写的字段都用默认值。运行前先把密钥放进环境变量 POPNOW_API_KEY。
示例里的 image_url, video_url 用的是 PopNow 的示例素材，换成你自己的公开 HTTPS 链接、上传文件或已保存的素材即可。
curl -X POST "https://api.popnow.ai/api/v1/jobs/createTask" \
-H "Authorization: Bearer $POPNOW_API_KEY" \
-H "Content-Type: application/json" \
-H "Idempotency-Key: $(uuidgen)" \
-d '{
"model": "kling/3.0/character-animation",
"input": {
"prompt": "The person dances with relaxed, natural movement",
"image_url": "https://media.popnow.ai/influencer/examples/marco.webp",
"video_url": "https://media.popnow.ai/effects/flower-bloom-1abd6efb.mp4",
"resolution": "720p"
}
}'响应里会立刻带回 taskId。之后用 GET /api/v1/jobs/recordInfo 取结果，或者在请求里加上 callBackUrl 等通知。
curl "https://api.popnow.ai/api/v1/jobs/recordInfo?taskId=TASK_ID_FROM_CREATE_TASK" \
-H "Authorization: Bearer $POPNOW_API_KEY"