grok-4.20
xAI
Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.
$2.125/ M
$4.25/ M
$0.34/ M
$0/ M
xAI Grok Imagine Video 1.5 generates video from text, a first-frame image, or up to three reference images.
Разрешение
480
720
Без видеовхода
Скидка 16%$0.0672/ M
$0.1176/ M
С видеовходом
Скидка 16%$0.0672/ M
$0.1176/ M
Ввод
Текст
Вывод
Видео
{
"model": "xai/grok-imagine-video-1.5",
"prompt": "晨曦微露的高山湖泊,湖面如镜倒映雪峰与流云,镜头沿湖岸缓缓横移,薄雾轻笼水面,金色阳光穿透云层洒落林间,远处飞鸟掠过天际,电影级画质,柔和自然光,4K 质感。",
"duration": 5,
"resolution": "480",
"aspect_ratio": "adaptive",
"generate_audio": true,
"seed": -1,
"group": "default"
}{}API
Готовый код для вызова этой модели через OpenAI-совместимый API EasyAPI.
Создайте API-токен в консоли и задайте его как переменную окружения:
Замените sk-xxxxxxxx на API-токен из консоли (Bearer Token).
Создать API-токенexport EASYAPI_API_KEY=sk-xxxxxxxxИспользуйте xai/grok-imagine-video-1.5 с API EasyAPI:
curl https://token.easyapi.com/v1/videos \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $EASYAPI_API_KEY" \
-d '{"model":"xai/grok-imagine-video-1.5","prompt":"A golden retriever running on a sunny beach, cinematic camera movement","duration":5,"resolution":"720p","aspect_ratio":"adaptive","generate_audio":false,"seed":-1,"size":"1280x720","input_references":[{"type":"image","url":"https://cdn.example.com/portrait.jpg","role":"first_frame"}]}'Отправляет задачу генерации видео по текстовому prompt.
https://token.easyapi.com/v1/videosBearer $EASYAPI_API_KEYapplication/jsonxai/grok-imagine-video-1.5根据 prompt 提交视频生成任务,响应含任务 ID 或结果 URL。 Документация
| Имя | Тип | Обяз. | Описание |
|---|---|---|---|
model | string | Да | 模型 ID,如 bytedance/seedance-2.0;当前使用 xai/grok-imagine-video-1.5 |
prompt | string | Да | 视频描述,建议包含主体、动作、场景、镜头和风格。不同模型上限不同:Sora 500 字,Hailuo 2000 字,Wan T2V 1500 字、I2V 800 字。Gate.AI 本身不设硬性上限,超出后由上游拒绝并透传 502 / 503。 |
duration | integer | Нет | 视频时长(秒),支持 4–15 |
resolution | string | Нет | 输出分辨率:480p、720p 或 1080p |
aspect_ratio | string | Нет | 宽高比:16:9、4:3、1:1、3:4、9:16、21:9 或 adaptive |
generate_audio | boolean | Нет | 是否生成音频 |
seed | integer | Нет | 随机种子,-1 到 4294967295;相同 seed 不保证完全一致 |
size | string | Нет | 精确输出尺寸,如 1280x720 |
input_references | array | Нет | 可选参考素材数组,用于图生视频、首尾帧驱动、视频风格迁移或音频驱动生成 |
input_references[].type | string | Да | 参考素材类型:image、video 或 audio,必须与 role 匹配 |
input_references[].url | string | Да | 参考素材的 HTTPS 地址 |
input_references[].role | string | Да | 参考素材用途:first_frame、last_frame、reference_video 或 reference_audio。first_frame/last_frame 各最多 1 个;last_frame 出现时必须同时提供 first_frame |
metadata | object | Нет | 业务透传字段,用于审计或来源标记 |
webhook_url | string | Нет | 任务完成或失败后的回调地址 |
Официальные SDK OpenAI и других работают при замене base URL. См. руководство по интеграции
xAI
Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.
$2.125/ M
$4.25/ M
$0.34/ M
$0/ M
xAI
Multi-agent variant that dispatches sub-agents in parallel for deep research, multi-step reasoning, and tool orchestration.
$3.4/ M
$10.2/ M
$0.34/ M
$0/ M
xAI
Reasoning-oriented Grok variant built for multi-step problem solving and agentic tool use, with strict prompt adherence and low hallucination.
$2.125/ M
$4.25/ M
$0.34/ M
$0/ M
xAI
Grok 4.3 is a reasoning model from xAI that supports text and image inputs with text output. It is suited for agentic workflows, instruction following, long-document analysis, and deep research. The model supports a 1M token context window. Requests above 200K total tokens are billed at a higher rate.
$2.125/ M
$4.25/ M
$0.34/ M
$0/ M