ApiframeApiframe Docs
Video Generation

Video Generation

Generate videos using a variety of models through a single unified endpoint.

POST /v2/videos/generate

Submit a prompt to generate a video. The request returns immediately with a job ID — poll the Jobs endpoint or use webhooks to get the result.

Common request body

FieldTypeRequiredDescription
promptstringYesThe video description (1–4,000 characters)
modelstringYesThe model identifier (see available models below)
webhookUrlstringNoURL to receive webhook notifications
webhookEventsstring[]NoEvents: "progress", "completed", "failed"

Each model also accepts its own parameters object — see the individual model pages for details.

Response

Status: 202 Accepted

{
  "jobId": "b2c3d4e5-f6a7-8901-bcde-f23456789012",
  "status": "QUEUED"
}

Available models

ModelIdentifierDescription
Grok Imagine Video"grok-imagine-video"xAI Grok Imagine — text-to-video and image-to-video with reference images
Hailuo 02"hailuo-02"MiniMax Hailuo 02 — text-to-video and image-to-video with end-frame support
Hailuo 2.3"hailuo-2.3"MiniMax Hailuo 2.3 — realistic motion and high-fidelity stylization
Hailuo 2.3 Fast"hailuo-2.3-fast"MiniMax Hailuo 2.3 Fast — speed-optimized variant
Luma Ray 2"luma-ray-2"Luma Ray 2 — text-to-video and image-to-video with camera concepts
Luma Ray Flash 2"luma-ray-flash-2"Luma Ray Flash 2 — faster, cost-effective variant of Ray 2
Kling 2.1"kling-2.1"Standard/pro modes with end-image support
Kling 2.1 Master"kling-2.1-master"Premium quality video generation
Kling 2.5 Turbo Pro"kling-2.5-turbo-pro"Fast, cost-effective with end-image support
Kling 2.6"kling-2.6"High-quality video generation with audio support
Kling 3.0"kling-3.0"Latest generation with flexible duration, modes, audio, and multi-prompt
Midjourney Video"midjourney-video"Image-to-video generation — 4 videos per request
Runway Gen-4 Turbo"runway-gen4-turbo"Runway Gen-4 Turbo — fast 720p text-to-video and image-to-video
Runway Gen-4.5"runway-gen4.5"Runway Gen-4.5 — flagship text-to-video and image-to-video model
Seedance 1 Lite"seedance-1-lite"ByteDance Seedance Lite with text-to-video and image-to-video support
Seedance 1 Pro"seedance-1-pro"Higher-quality Seedance v1 generation with dynamic pricing by resolution and duration
Seedance 1 Pro Fast"seedance-1-pro-fast"Faster Seedance v1 variant with text-to-video and image-to-video support
Seedance 1.5 Pro"seedance-1.5-pro"Seedance 1.5 Pro with optional synchronized audio generation
Seedance 2.0"seedance-2"Seedance 2.0 with multimodal references, native audio, web search, and adaptive aspect ratio
Seedance 2.0 Fast"seedance-2-fast"Seedance 2.0 Fast — speed-optimized variant with multimodal references and audio
Sora 2"sora-2"OpenAI Sora 2 with text-to-video and image-to-video support
Sora 2 Pro"sora-2-pro"OpenAI Sora 2 Pro with standard and high resolution variants
Veo 2"veo-2"Google Veo 2 — text-to-video and image-to-video
Veo 3"veo-3"Google Veo 3 — video generation with audio support
Veo 3 Fast"veo-3-fast"Google Veo 3 Fast — faster generation with audio
Veo 3.1"veo-3.1"Google Veo 3.1 — audio, reference images, last-frame control
Veo 3.1 Fast"veo-3.1-fast"Google Veo 3.1 Fast — speed-optimized with full features
Wan 2.5"wan-2.5"Alibaba Wan 2.5 — text-to-video and image-to-video with audio sync
Wan 2.5 Fast"wan-2.5-fast"Alibaba Wan 2.5 Fast — speed-optimized variant
Wan 2.6"wan-2.6"Alibaba Wan 2.6 — up to 15s with multi-shot storytelling and audio
Wan 2.6 Flash"wan-2.6-flash"Alibaba Wan 2.6 Flash — fast image-to-video with optional audio

Error responses

StatusErrorMeaning
400Validation errorInvalid parameters
401UnauthorizedMissing or invalid API key
402Insufficient creditsNot enough credits
503Service unavailableQueue temporarily down

On this page