通过统一的接口调用多家顶级视频生成模型,支持文生视频、动作控制等能力。
所有请求需在 Header 中携带 Bearer Token:
Authorization: Bearer YOUR_API_KEY
/api/v1/video/generations创建视频生成任务
/api/v1/video/generations?task_id=xxx查询任务状态并获取视频链接
/api/v1/video/p-video同步P-Video 专属同步接口:单次请求阻塞约 30-60 秒,直接返回视频链接,无需轮询
选择模型提供商查看对应的参数和示例
xAI 出品的高质量文生视频模型,支持 5秒/10秒/15秒 视频生成,动作自然流畅。
grok-video-3grok-video-3-10s# Step 1: Create task
curl -X POST https://apimodels.app/api/v1/video/generations \
-H "Authorization: Bearer YOUR_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "grok-video-3",
"prompt": "A cat playing piano in a jazz club, cinematic lighting",
"aspect_ratio": "16:9"
}'
# Step 2: Poll status
curl "https://apimodels.app/api/v1/video/generations?task_id=TASK_ID" \
-H "Authorization: Bearer YOUR_API_KEY"{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "pending"
}
}{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "completed",
"resultUrls": ["https://cdn.example.com/video.mp4"],
"createTime": 1705123450000,
"completeTime": 1705123500000
}
}{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"state": "failed",
"failMsg": "Content policy violation"
}
}在创建请求中传入 callback_url 后,任务进入 completed 或 failed 终态时,我们会向该地址发起一次 HTTP POST。请求头仅包含 Content-Type: application/json,无签名头。失败会自动重试 3 次(指数退避 1s/2s/4s,单次超时 10s);如果仍未成功,后台会在 30 分钟内继续补偿重发,直到接收端返回 2xx。
POST {your callback_url}
Content-Type: application/json
{
"code": 200,
"msg": "success",
"data": {
"taskId": "clxxx...",
"model": "<provider>/<model_name>",
"state": "completed" | "failed",
"param": "<JSON string>", // request params, JSON.parse once
"resultJson": "<JSON string> | null", // result object, JSON.parse once
"failCode": null | "CONTENT_MODERATION | INVALID_INPUT | INSUFFICIENT_BALANCE | UPSTREAM_BUSY | UPSTREAM_FAILED | TIMEOUT | INTERNAL_ERROR | OTHER",
"failMsg": null | "string",
"retryable": true | false, // present when state=failed: safe to retry/fallback
"costTime": 12345, // duration in ms
"completeTime": 1705123500000, // ms epoch
"createTime": 1705123450000 // ms epoch
}
}注意:data.param 与 data.resultJson 都是 JSON 字符串,使用前必须 JSON.parse 一次。
{
"resultUrls": ["https://r2.apimodels.app/videos/xxx.mp4"],
"thumbnailUrl": "https://...jpg", // optional (some models only)
"videoSize": "1280x720", // optional
"videoDuration": 5, // optional, seconds
"videoModel": "veo3" // optional
}resultUrls 始终存在,长度通常为 1(失败时为空数组)。其它字段可选,按上游不同会缺失,请按需读取。state=failed 时 resultJson 通常为 null 或 {"resultUrls":[]},请不要假设一定有视频链接。
app.post('/webhook/video', express.json(), (req, res) => {
const { taskId, state, resultJson, failMsg } = req.body.data
if (state === 'completed') {
const r = JSON.parse(resultJson)
console.log('video ready', taskId, r.resultUrls[0], r.videoDuration)
} else {
console.warn('video failed', taskId, failMsg)
}
res.status(200).end() // must be 2xx, otherwise we retry
})pending任务已排队,等待处理processing视频生成中completed生成成功,可获取视频链接failed生成失败400请求参数错误或缺失401API 密钥无效402积分不足404任务 ID 不存在500服务器内部错误下列所有模型通过统一 API、一个 key 即可调用。点击模型查看完整 playground 与文档。
| 模型 | model 参数 | 价格 | 说明 |
|---|---|---|---|
| Grok Imagine Video 1.5 | grok-imagine-video-1.5 | $0.098/s+ | xAI Grok Imagine Video 1.5 Preview — image-to-video with native synchronized audio. #1 on the Image-to-Video Arena, with lifelike motion, strong prompt adherence and consistent characters. 480p / 720p, 1-15s. |
| Grok Imagine Video 1.5(Beta) | grok-imagine-video-1.5-beta | $0.35+ | Grok Imagine Video 1.5 (Beta) — an alternative stable channel for xAI Grok image-to-video. Turn one reference image into a cinematic clip with an optional prompt. Simple flat per-clip pricing by duration (5 / 8 / 10 / 12 / 15s), 480p or 720p. |
| LTX-2.3 视频 | ltx-2.3 | $0.02/s+ | LTX-2.3 unified text-to-video and image-to-video. Send a prompt for T2V, or add one reference image for I2V — fast, with 480p / 720p / 1080p output. Billed per second by resolution. |
| Seedance 2.0 | seedance-2.0 | $0.13/s+ | The fullest, most all-around capable Seedance 2.0 channel — full multimodal generation from text, a first / first+last frame, up to 9 reference images, reference video, reference audio, web search and native audio. Supports real people and asset creation. 480p / 720p / 1080p, 4-15s, per-second pricing. |
| Seedance 2 Mini | seedance-2-mini | $0.042/s+ | ByteDance Seedance 2 Mini — multimodal text / image / video / audio → video with native AI audio. Reference images, reference video and reference audio, web search, 480p / 720p, 4-15s. Per-second pricing by resolution and whether AI audio is generated. |
| Seedance 2.0 Fast | seedance-2.0-fast | $0.11/s+ | The faster, cheaper variant of the fullest Seedance 2.0 channel — same full multimodal capability (text / first+last frame / up to 9 reference images / reference video / reference audio / web search / native audio), supports real people and asset creation. 480p / 720p, 4-15s, per-second pricing. |
| Seedance 2.0 (Official) | seedance-2.0-official | $0.092/s+ | ByteDance Seedance 2.0 cinematic video — direct official Volcengine API, stable and high-concurrency. Text, image and multimodal generation with friendly per-second pricing. |
| Seedance 2.0 · sd-A | seedance-2.0-a | $0.073/s+ | Seedance 2.0 sd-A — full multimodal HD video (720p / 1080p) with an in-playground tier switch (2.0 / Fast / Mini): text, first/last frame, up to 9 reference images + video + audio, web search, native audio, and asset-library characters. |
| 全能视频 Omni Flash | gemini-omni-flash | $0.20+ | Gemini Omni Flash — unified video generator for text-to-video, image-to-video (1 or 3 reference images) and video editing. 720p / 1080p, 4 / 6 / 8 / 10s, optional 16:9 or 9:16 framing. Simple per-duration pricing ($0.20–0.45); video edit a flat $0.60. |
| 全能视频 Omni Flash 稳定版 | gemini-omni-video | $0.35+ | Omni Flash (Stable) — lower-cost, full-suite Gemini Omni video. Text / image (up to 7 refs) / video-to-video, plus reusable voices and consistent characters. 720p / 1080p / 4k, 4 / 6 / 8 / 10s, 16:9 or 9:16, optional seed. |
| Seedance 2.0 影视版 | seedance-2.0-beta | $1.00+ | Film-grade edition of Seedance 2.0 — cinematic lighting, mood and camera motion, and it ACCEPTS real-person / realistic human reference images (unlike Ark-direct Seedance 2.0, which rejects real faces). Up to 4 reference images for identity-locked image-to-video — ideal for film-grade portrait and character work. Quality tier sits above the Ark variants; generation takes longer (typically 60-180s). Use only with consented subjects. |
| 视频字幕擦除 | subtitle-erase | $0.01/s | Remove hardcoded subtitles and burned-in on-screen text from any video, leaving a clean background. Pick subtitle-only or any-text mode, quality or smaller-size output, and optionally target only chosen regions. Billed $0.01 per second of input video. |
| Seedance 2.0 Fast (Official) | seedance-2.0-fast-official | $0.071/s+ | Seedance 2.0 Fast — direct official Volcengine API, faster and lower-cost. Text, image and multimodal video generation, stable under high concurrency. |
| VEO 3.1 Fast HD | veo-3.1-fast-hd | $0.07 | VEO 3.1 Fast HD (720p) video generation. 8s fixed duration, 16:9 aspect ratio, reference image support. |
| VEO 3.1 Fast Full HD | veo-3.1-fast-fhd | $0.07 | VEO 3.1 Fast Full HD (1080p) video generation. 8s fixed duration, 16:9 aspect ratio, reference image support. |
| VEO 3.1 Fast 4K (Beta) | veo-3.1-fast-beta | $0.07-$0.10 | VEO 3.1 Fast 4K video generation. Requires start frame image. Supports start-end frame video generation. |
| P-Video | p-video | $0.05+ | Fast video generation in ~10 seconds. Text/image/audio-to-video with draft mode for 4x faster previews. Built-in audio generation, up to 1080p 48FPS. |
| DreamActor V2 (Motion Transfer) | dreamactor-v2 | $0.06/s | ByteDance DreamActor V2 motion transfer. Drive any character image with reference video motion, supporting multi-person, anime and pets. |
| Kling Motion Control | kling-motion-control | $0.06/s+ | Generate videos with character motion control. Provide a reference image and motion video to create animated content. |
| Kling V3 Omni | kling-v3-omni | $0.15/s | Kling V3 Omni-Video with extended duration and keep-original-sound support for video editing. Flat $0.15/s billing. |
| Kling V3 | kling-v3 | $0.12/s+ | Latest Kling V3 video generation. Supports 3-15s flexible duration, text-to-video and image-to-video with optional audio. |
| Omni Video V3.1-fast (Start-End Frame, Budget) | veo-3.1 | $0.30 | High-performance start-end frame video. Provide first + optional last frame, the model interpolates motion between them in seconds. Budget channel — cheaper than the official VEO, less stable. |
| Omni Video V3.1-Lite (Start-End, Official Stable) | omni-video-v3.1-lite | $0.72-$1.152 | Smooth cinematic transitions between a required first frame and required last frame. Outputs 720p or 1080p with native audio. Official stable channel — pricier than V3.1-fast but reliable, ideal for production. |
| Grok Video 3 (10s) | grok-video-3-10s | $0.10 | Grok Video 3. 10-second video at $0.01/s. Supports text-to-video and image-to-video (up to 7 reference images). |
| Grok Video 3 | grok-video-3 | $0.06-$0.15 | Grok Video 3. Per-second pricing $0.01/s, 6 / 10 / 15 second output. Both T2V (omit images) and I2V (1-7 reference images) supported. |
| Kling Lip-Sync Video | rh-lip-sync-video | $0.065/5s | Kling AI lip-sync video generation. Frame-level lip synchronization with audio for real humans, 3D and 2D characters. |
| AI Lip-Sync | ai-lipsync | $0.02/s | Turn a portrait image + an audio clip into a talking-head video. The output length follows the audio; billed per second. |
| Kling Lip-Sync TTS | rh-lip-sync-tts | $0.01 | Kling text-to-speech synthesis with multi-language support, voice cloning, speed control and emotion styles. |