Kling AI NEW API Specification
⚠
Notice:
1.The API endpoint for the new system has been updated from https://api.klingai.com to https://api-singapore.klingai.com.
Update Time | Update Notes |
09/10/2026 | ●10 video effects have been updated: 3d_cartoon_2,guardian_spirit,pet_dance,running_man,pet_moto_rider,swing_swing,day_to_night,throne_of_king,skateskate,surfsurf.For pricing changes, please refer to the Effects Pricing List ●For video effects details, refer to: Video Effects Center |
09/04/2026 | ●Launch of 9 new video effects: net_the_fish,birthday_board,summer_fireworks,blow_blaze,champagne_birthday,pet_working_daily,pet_roll_window,pet_crash_earth,barbie_transform ●For video effects details, refer to: Video Effects Center |
08/21/2026 | ●Launch of 3 new video effects: makeup_style,hair_dressup,barbie_transform ●For video effects details, refer to: Video Effects Center |
08/07/2026 | ●Launch of 1 new video effects: magic_world_vlog_9_16 ●For video effects details, refer to: Video Effects Center |
08/03/2026 | ●Launch of 3 new video effects: critter_paste, wiggle_faces_pets, paw_headbang ●For video effects details, refer to: Video Effects Center |
07/24/2026 | ●Launch of 9 new video effects: food_splash, dj_pet, pet_diving, disco_paws, pet_fitness, j_var_live,pet_burst, idol_live, puff_cheeks ●For video effects details, refer to: Video Effects Center |
07/03/2026 | ●Launch of 4 new video effects: african_sway, jealousy_sway, chubby_fish, shrug_dance, beast_striker ●For video effects details, refer to: Video Effects Center Notice: magic_match_tree will be discontinued on July 3rd, 2026 |
06/25/2026 | ●Launch of 1 new video effects: soccer_star ●For video effects details, refer to: Video Effects Center |
06/18/2026 | ●Launch of 8 new video effects: bra_hot_dance, arg_hot_dance, fra_hot_dance, bra_goal, arg_goal, por_goal, victory_slide, samba_fever ●For video effects details, refer to: Video Effects Center |
06/12/2026 | ●Launch of 3 new video effects: bicycle_kick, football_dance_2, red_card_sent_off ●For video effects details, refer to: Video Effects Center |
06/05/2026 | ●Launch of 4 new video effects: football_dance, magic_world_vlog, air_dunk, whirling_beverage_9_16 ●For video effects details, refer to: Video Effects Center |
05/20/2026 | ●Launch of 2 new video effects: tennis_trend, tennis_trend_9_16 ●Special Effects Optimization: ○korean_baseball: support for animal image input ○football_live: Optimized jersey design ○football_live_9_16: Optimized jersey design ●For video effects details, refer to: Video Effects Center |
05/15/2026 | ●Launch of 2 new video effects: football_live_9_16, whirling_beverage ●For video effects details, refer to: Video Effects Center |
05/14/2026 | ●Launch of 2 new video effects: f1_live, football_live ●For video effects details, refer to: Video Effects Center |
05/13/2026 | ●Launch of 2 new video effects: korean_baseball_9_16、spielberg_transition ●For video effects details, refer to: Video Effects Center |
05/11/2026 | ●Launch of 1 new video effects: korean_baseball ●For video effects details, refer to: Video Effects Center |
05/08/2026 | ●Launch of 2 new video effects: pet_skateboard and daily_ootd ●For video effects details, refer to: Video Effects Center |
05/07/2026 | ●Remove the mutual exclusion between the "multi-shot" and "first and last frames" functions, allowing users to set the content of the first and last frames when generating multi-shot videos ●Supported model ranges: kling-v3-omni, kling-v3 |
04/27/2026 | ●Implementation method: Set the value of the series_amount parameter to auto ●When using auto, it will occupy a concurrency amount corresponding to the actual generated quantity |
04/24/2026 | ●Launch of 17 new video effects: tiny_beast_printer, landmark_reveal, winter_charm, flash_ride, shooting_star, sovereign_scepter, return_of_the_king, minimalist_light, martial_meow, knock_at_a_door_revenge,sassy_shake, etc ●For video effects details, refer to: Video Effects Center |
04/23/2026 | ●Implementation method: Set the mode parameter value to 4k, and you can generate a video with high expressiveness and a resolution of 4K, just like in PRO mode ●Support scope: ○Omni-Video: The kling-v3-omn model supports all functions except for "reference video"; ○Text-to-Video: kling-v3 model; ○Image-to-Video: kling-v3 model; ● Billing policy: Charged based on the duration of the generated video, with 3 units deducted per second. |
04/08/2026 | ●Launch of 17 new video effects: perler_beads,spring_bloom, palm_sized_figure_pro, prank_box, lucky_veggie, toss_run, switch_to_silk, studio_look, etc ●For video effects details, refer to: Video Effects Center |
04/01/2026 | ●For details, see the parameter descriptions for the image_list and element_list parameters. ●This update only provides detailed explanations, and remains consistent with the original logic. |
03/23/2026 | ●Previously, only video character elements supported binding to voices. ●The voice binding method for multi-image elements is consistent with that of video character elements, and can be achieved by passing parameters through element_voice_id |
03/18/2026 | ●Launch of 6 new video effects: flash_drive, shush_my_dreams, french_elegance, finger_swipe, advent_of_flora, smooth_transition ●For video effects details, refer to: Video Effects Center |
03/11/2026 | ●When the value of the shot_type parameter is set to intelligence, intelligent storyboarding can be achieved Video Generation | Elaborate on some business logic descriptions ●When generating the start & end frames of a video using the kling-video-o1 model, referencing a element is not supported. ●Customizing elements through video only supports the creation of realistic-style, humanoid element. ●In the code for Create Element API, the format of the `element_voice_id` parameter is set to string. ●Multi-camera does not support the start & end frames. ●When the image is not the first or last frame, do not pass the type parameter. ●Description of the model range supported by the tone control function. |
03/04/2026 | ●You can enhance element consistency by binding the element, and when binding the element, you can only refer to the orientation of the person in the video. ●Add the model_name parameter to distinguish model versions, with a default of kling-v2-6. ●For generating STD mode motion control videos, 0.9 units will be deducted per second; for generating PRO mode motion control videos, 1.2 units will be deducted per second. |
02/27/2026 | ●Launch of 1 new video effects: raid_check ●For video effects details, refer to: Video Effects Center |
02/25/2026 | ●Supports the creation of elements through video, and when creating elements, it is possible to bind voice and use them to specify the voice during video generation. ●Upgrade the creation element to an asynchronous service to fulfill more element-related functions. ●The new element service adopts a brand-new API (advanced-custom-elements). The existing API can still be used normally, but the elements library is relatively independent and cannot perform cross-API queries. |
02/11/2026 | ●Launch of 10 new video effects: snow_night_kiss, eternal_kiss, fortune_in_motion, chinese_trend, sedan_chair_dance, skyfall, good_luck_dance, laicai_dance, yangge_dance, and horse_year_dance ●For video effects details, refer to: Video Effects Center |
02/04/2026 | ●Launch of 9 new video effects: unique_firework, palm_sized_figure, color_mixing, lantern_festival_cuju, tangyuan_to_animal, etc ●For video effects details, refer to: Video Effects Center |
02/03/2026 | ●Launch of 9 new video effects: hot_feet_dance, swag_dance, pigeon_dance, chanel_dance, city_to_village, etc ●For video effects details, refer to: Video Effects Center |
01/27/2026 | ●Launch of 7 new video effects: new_year_feast, ring_in_new, pet_vlogger, crystal_horse, lateral_shift_transitionl,horse_year_firework, etc ●For video effects details, refer to: Video Effects Center |
01/23/2026 | ●Through the front view of the element, other angle images of the element can be automatically inferred, and three sets of results can be generated for selection each time. ●Charged based on the times of service visits, with 0.5 units deducted per visit. General | New Capability: When querying the task results, you can directly obtain the units consumed by the current task ●The key of JSON parameter is: final_unit_deduction. General | New feature: When generating images or videos, a watermark can be added simultaneously ●When the enabled parameter in watermark_info is set to true during parameter input, a watermarked result can be generated simultaneously. ●The watermark_url parameter of the returned result is the watermarked version. ●Currently, only some APIs support watermarking. For details, please refer to the current API documentation. |
01/16/2026 | ●Launch of 31 new video effects: drunk_dance, daoma_dance, lion_dance, lucky_money_come, phantom_jewel, zoom_out, etc ●For video effects details, refer to: Video Effects Center |
12/22/2025 | ❗ Please note that in order to ensure the quality of generation, the current motion control function has a relatively strict detection mechanism for the input reference images and videos. If the detection fails, generation will not proceed (no API fees will be charged). Please refer to the requirements for images and videos in the [User Guide] for proper usage.    ●Based on the new API path, both reference images and reference videos need to be uploaded simultaneously. ●Supports standard mode and high-quality mode. When generating standard mode videos, 0.5 points are deducted per second, and when generating high-quality mode videos, 0.8 points are deducted per second. The seconds are rounded to the nearest integer. ●The upper limit of the reference video duration is related to the orientation of the generated video characters: up to 30 seconds when consistent with the reference video, and only 10 seconds when consistent with the reference image. ●Action libraries are not currently supported. |
12/18/2025 | ●Launch of 16 new video effects: cheers_2026, countdown_teleport, santa_random_surprise, birthday_star, etc ●Notice:kiss,fight,hug,thumbs_up,tiger_hug,pet_lion, 3d_cartoon_1 will be discontinued on January 30, 2026 ●For video effects details, refer to: Video Effects Center |
12/16/2025 | ●By using prompt and voice_list, a specified voice can be used to generate videos: 6 units will be deducted for 5 seconds, and 12 units will be deducted for 10 seconds. ●Supports voice customization and can also use system preset voice. |
12/15/2025 | ●Supports Text-To-Video and Image-To-Video. ●Control whether to include audio when generating videos through the sound parameter. ●New API, multiple feature can be achieved through prompt words alone. ●New API, multiple feature can be achieved through prompt words alone. |
12/11/2025 | ●Launch of 20 new Christmas, New Year, and Winter-themed effects: firework_2026, santa_gift, scarlet_and_snow, etc ●Notice:celebration and c4d_cartoon will be discontinued on December 30, 2025 ●For video effects details, refer to: Video Effects Center |
12/04/2025 | ●No sensory upgrade, no need to modify API parameters |
11/25/2025 | ●Launch of “Single Image Effects”:balloon_parade, jumping_ginger_joy, bullet_time, etc. ●For video effects details, refer to: Video Effects Center |
11/19/2025 | ●Launch of “Single Image Effects”:luminous_elf, guardian_spirit, snowboarding, etc. ●For video effects details, refer to: Video Effects Center ●Deduct 16 units when generate a image |
11/17/2025 | ●Passing in the image parameter value and image_tail parameter value can achieve this ●Deduct 2.5 units when generate a 5-second video,and deduct 5 units when generate a 10-second video |
11/11/2025 | ●Including "Text-To-Video" and "Image-To-Video" ●Deduct 1.5 units when generate a 5-second video,and deduct 3 units when generate a 10-second video |
11/3/2025 | ●No need to modify any code. |
10/27/2025 | ●Launch of 10 Halloween special effects: pumpkin_head_transform, cute_ghost_transform, knock_knock_halloween, halloween_escape, etc. ●For video effects details, refer to: Video Effects Center |
10/20/2025 | ●Support PRO mode, generate 5-second video with as low as 2.5 units ●For recognize subjects, faces, clothing, etc., and can receive 4 sets of results per request ●For Multi-Image to Video and Multi-Elements functions |
10/15/2025 | ●Launch of “Single Image Effects”: inner_voice, trampoline, guess_what, etc. ●For video effects details, refer to: Video Effects Center ●Generate videos based on images, audio, or text that have natural facial expressions, consistent rhythms, and vocals. ●It‘s currently not supported to specify faces if there are multiple faces in the input image. |
09/28/2025 | ❗ Notice: To ensure data security, all images and videos generated via our API will be automatically purged after 30 days. To avoid any disruption to your service, please download and save them locally in a timely manner after generation |
09/28/2025 | ●Launch of “Single Image Effects”:feed_mooncake ●For video effects details, refer to: Video Effects Center |
09/26/2025 | ●Launch of “Single Image Effects”:rampage_ape, flyer, and dishwasher ●For video effects details, refer to: Video Effects Center |
09/12/2025 | Video Generation | Video Effects | New Feature ●Launch of “Single Image Effects”: gallery_ring, squeeze_screamt, etc. ●For video effects details, refer to: Video Effects Center |
09/11/2025 | ●Lip-Sync | Feature Update：Support multi person screen lip-sync and start lip-sync time ○Specify the speaker through face_id and start lip-sync time through sound_insert_time ○Support clipping audio ●TTS | New Feature: Online text-to-speech and enable trial listening function ○Can generate audio_id simultaneously, can be used for any Kling API |
09/05/2025 | ●Video Generation | New Feature: V2.1 supports start/end frame ○Supports generating 5s or 10s video, Only supports PRO mode ●Video Generation | Feature Update: Video-to-Audio ○Users can input their own sound effect prompts, bgm prompts, and enable ASMR mode. |
09/01/2025 | Video Generation | Video Effects | New Feature ●Launch of “Single Image Effects”: pet_chinese_opera, muscle_pet, etc. ●For video effects details, refer to: Video Effects Center |
08/19/2025 | Video Generation | Video Effects | New Feature ●Supports 62 new single image effects and 1 dual-character effect, expanding the library to 80 callable effects. ●Launched the ‘Video Effects Center’ page, where users can view effect details and units for API calls: Video Effects Center |
08/15/2025 | ●Video Generation | Feature Update: Video-to-Audio ○Video-to-Audio feature supports full-resolution video uploads ●Multi-Image to Video | Feature Update: show a 102% performance improvement over the previous feature ○Subject consistency, dynamics, prompt adherence, style consistency, and visual rendering are better ○No code changes are required ●Image Generation | Model Update: New V2.0 Image-to-Image supports nearly 300 styles ○Parameter example: "model_name": "kling-v2-new" |
08/12/2025 | ●Video Generation | Feature Update: T2V V1.6 supports PRO ○Parameter example: "mode": "pro" ○Supports generating 5s and 10s video |
08/01/2025 | ●Video Generation | New Feature: Text-to-Audio ○Supports generating audio by text prompts ●Video Generation | New Feature: Video-to-Audio ○ Supports adding audio to all videos generated by Kling models ○Supports adding audio to user-uploaded videos |
7/30/2025 | ●Image Generation | Support V2.1 model ○Update image2image kling-v2-1 model ●Multi-Image to Image | Newly launched ○Support subject reference, scene reference and style reference ○Deduct 16 units from total, about $0.056 ○Only support kling-v2-1 model |
7/21/2025 | ●Video Generation | Video Effects | New Feature ○Launch of "Single Image Effects": 7 types available, jelly_press, jelly_slice, jelly_squish, jelly_jiggle, pixelpixel, yearbook, instant_film ○ncludes create task, query task (single), and query task (list) interfaces ●Multi-Elements | Newly launched ○Support adding (addition), swapping (swap), and removing (removal) elements to existing videos ○When using, it is necessary to initialize the video and tag it before performing operations such as creating tasks |
● | |
7/7/2025 | ●Video Generation - Video Effects | New Feature ○Launch of "Single Image Effects": 2 types available, anime_figure, rocketrocket ○ncludes create task, query task (single), and query task (list) interfaces |
6/30/2025 | ●Lip-Sync | New version new capabilities ○Supports increasing the maximum video duration from 10 seconds to 60 seconds ○Generating videos takes as little as 2 minutes ○No need to modify the code |
6/19/2025 | ●Video Generation | Support V2.1 model ○Update image2video kling-v2-1 model, supports STD mode and PRO mode ○Update image2video kling-v2-1-master model ○Update text2video kling-v2-1-master model |
6/6/2025 | Image Generation | Support V2.0 Image-To-Image Model Image Generation | V2.0 Text-To-Image model supports selecting resolutions (1K, 2K) Image Generation | Support Image Expasion |
5/13/2025 | Image Generation | Support V2.0 model ○Support kling-v2 text-to-image Video Generation | Support V2.0 model ○Support kling-v2 text-to-video and image-to-video ○Kling-v2 currently does not support mode parameter Multi-Image to Video | Newly launched ○Supports selecting subjects from up to 4 images ○Support custom generated video aspect ratios: 16:9, 9:16, 1:1 |
4/25/2025 | Video Generation - Video Effects | New Feature: bloombloom & dizzydizzy (Single Image Effect) ○Launch of "Single Image Effects": 2 types available, bloombloom, dizzydizzy ○ncludes create task, query task (single), and query task (list) interfaces |
3/31/2025 | Video Generation | V1.6 model supports generating videos from end frame ○V1.6 model PRO mode can be used to generate video footage of the first few seconds of an image based on the image Video Generation | V1.5 and V1.6 models support video extension ○Videos generated based on V1.5 and V1.6 models can be continued for 4-5 seconds after writing ○If the video is generated using "last frame only", continue writing the content of the previous 4-5 seconds |
3/25/2025 | Image Generation | V1.5 model supports character feature reference and character appearance reference ○Selecting Face as reference: you can keep the face consistent with the reference image, and use prompt to change other components like the outfit and the background; great for single-character consistency across different looks ○Selecting Subject as reference: you can set the entire subject as reference, and even fine-tune the reference level on the face and the subject; great for keeping the appearance of the character consistent across different scenes |
3/18/2025 | Video Generation - Video Effects | New Feature: fuzzyfuzzy（Single Image Effect） ○Launch of "Single Image Effects": fuzzyfuzzy ○Includes create task, query task (single), and query task (list) interfaces |
3/12/2025 | Video Generation - Video Effects | New Feature: Single Image Effect ○Launch of "Single Image Effects": 2 types available, squish, expansion ○Includes create task, query task (single), and query task (list) interfaces Video Generation | New models supports start/end frame, end frame, motion brush, camera control ○V1.5 Model PRO mode supports start/end frame, end frame, motion brush, camera control(simple only) ○V1.6 Model PRO mode supports start/end frame Video Generation | Lip-syncing supports customized videos and more available tones ○Supports lip-syncing for any 1080p or 720p video within 10s ○Added 8 new Chinese and English tones that can be used directly to dub lip-sync videos Image Generation | Support V1.5 model ○Improved aesthetics: better composition and lighting, especially more aesthetically pleasing in portraits ○Improved image quality: enhanced fidelity in details, more natural rendering, and stronger tonal contrast ○Support 21:9 aspect ratio |
3/5/2025 | Video Generation | New Feature: Creative Video Effects ○Launch of "Dual-character Effects": 3 types available, "hug", "kiss", and "heart_gesture". ○Includes create task, query task (single), and query task (list) interfaces ⭐ Compared to the general video generation API, the video effects API provides more flexible calling parameters and integrates pre- and post-processing functionalities tailored for special effects (e.g., dual-character effects). For example, it allows users to input two portrait images, automatically stitches them into a single composite image, and generates the video using the stitched image. This makes the API more flexible and efficient. |
2/14/2025 | Image Generation | The "model" field has been changed to "model_name" ❗ Please note that in order to maintain naming consistency, the original model field has been changed to model_name, so in the future, please use this field to specify the version of the model that needs to be called. ●At the same time, we keep the behavior forward-compatible, if you continue to use the original model field, it will not have any impact on the interface call, there will not be any exception, which is equivalent to the default behavior when model_name is empty (i.e., call the V1 model). |
1/7/2025 | ●Supports text-to-video STD mode, image-to-video STD mode, and image-to-video PRO mode ●Currently does not support tail frame, motion brushes, camera control, and other control features ❗ Please note that in order to maintain naming consistency, the original model field has been changed to model_name, so in the future, please use this field to specify the version of the model that needs to be called. ●At the same time, we keep the behavior forward-compatible, if you continue to use the original model field, it will not have any impact on the interface call, there will not be any exception, which is equivalent to the default behavior when model_name is empty (i.e., call the V1 model). |
12/30/2024 | Virtual Try-On | New V1.5 model ●V1.5 model is a comprehensive upgrade of V1.0 model ●V1.5 model supports single clothing (upper, lower, and dress dress) try-on, as well as "upper + lower" combination try-on |
12/23/2024 | Video Generation | New Feature: Lip-Sync ●Videos generated by the Kling V1.0 model and Kling V1.5 model support lip-sync as long as the video meets the facial requirements ●Includes create task, query task (single), and query task (list) interfaces |
12/9/2024 | Video Generation | Kling V1.5 Std Model Now Open for Video Generation: Image-to-Video Functionality Enabled, Text-to-Video Unsupported ●Supports standard mode ●Tail frame control is not supported ●All other parameters are supported ❗ Please note that in order to maintain naming consistency, the original model field has been changed to model_name, so in the future, please use this field to specify the version of the model that needs to be called. ●At the same time, we keep the behavior forward-compatible, if you continue to use the original model field, it will not have any impact on the interface call, there will not be any exception, which is equivalent to the default behavior when model_name is empty (i.e., call the V1 model). |
12/2/2024 | Video Generation | Capability Map ●With multiple versions of the video generation model (V1, V1.5) and various plugin capabilities (e.g., camera control, start/end frame, motion brush, video extension, etc.), we have created a "Capability Map" to make it easier for everyone to visually check the availability of different versions and features. For details, please refer to the "3-0 Capability Map." |
11/29/2024 | Video Generation - ImageToVideo | New Feature: Motion Brush ●This feature is only supported in Standard Mode 5s and Professional Mode 5s for the V1.0 model, and is currently not available for the V1.5 model. |
11/15/2024 | Video Generation | Kling V1.5 Pro Model Now Open for Video Generation: Image-to-Video Functionality Enabled, Text-to-Video Unsupported ●Only supports professional mode ●Tail frame control is not supported ●All other parameters are supported Video Generation | New Feature: Video Extension ●Supports extending videos generated by the V1.0 model directly, adding 4-5 seconds of video length per extension ●Includes create task, query task (single), and query task (list) interfaces Video Generation | Other Updates ● Added "external_task_id" field, allowing you to customize a task ID when creating a task, and query the video using this custom ID when needed ❗ Please note that in order to maintain naming consistency, the original model field has been changed to model_name, so in the future, please use this field to specify the version of the model that needs to be called. ●At the same time, we keep the behavior forward-compatible, if you continue to use the original model field, it will not have any impact on the interface call, there will not be any exception, which is equivalent to the default behavior when model_name is empty (i.e., call the V1 model). |
10/30/2024 | Added the "Query Resource Package List and Remaining Quantity" interface for your convenience. See "Section VI: Account Information Query". |
10/25/2024 | To clarify the storage duration of model-generated content (images/videos): ●To ensure information security, generated images/videos will be cleared after 30 days. Please make sure to save them promptly. |
10/15/2024 | Add a sample Java code for generating the API_Token. |
9/19/2024 | Video Generation ●When creating a task, the character limit for the prompt and negative_prompt in the request parameters has been updated to: cannot exceed 2500 characters. |
9/19/2024 | Officially supporting the "AI Virtual Try-on" related API (kolors-virtual-try-on). |
I. General Information
1.API Domain
💎
https://api-singapore.klingai.com
⚠️Notice: The API endpoint for the new system has been updated from https://api.klingai.com to https://api-singapore.klingai.com.This API is suitable for users whose servers are located outside of China.
2.API Authentication
●Step-1：Obtain AccessKey + SecretKey
●Step-2：Every time you request the API, you need to generate an API Token according to the Fixed Encryption Method, Authorization = Bearer <API Token> in Requset Header
●Encryption Method：Follow JWT（Json Web Token, RFC 7519）standard