AI video generation APIs, with one key.
Compare published video models, supported workflows and billing tiers. Find the right request contract for your application and test generation in the Playground.
Choose a model for your workflow
Output and controls
Check the model-specific controls for text or image input, duration, resolution and audio. Available settings differ between models and versions.
Comparable costs
Compare the same duration, resolution and audio settings. Per-second and per-request prices need different calculations; use the listed tier parameters.
Integration requirements
Video generation uses asynchronous tasks. Store the task ID, handle pending and terminal states, and retrieve the video only after a successful result.
Explore 11 available models
Veo 3.1
Generate 4, 6, or 8-second videos with native audio from text, images, or references at 720p, 1080p, or 4K.
Seedance Pro Fast
ByteDance
Generate silent 5 or 10 second videos at up to 1080p from text or a single first frame with ByteDance Seedance 1.0 Pro Fast, built for fast, low-cost iteration.
Seedance 1.5 Pro
ByteDance
Generate 5-12 second 480p or 720p videos with synchronized dialogue, sound effects, and music from text or first and last frames with Seedance 1.5 Pro.
Kling AI
Kuaishou
Kling VIDEO 2.6 generates 5 or 10 second clips with optional native audio, including dialogue, narration, and sound effects, from text or one image.
WAN 2.6 Flash
Alibaba
Turn one image into a silent 2-15 second Wan 2.6 Flash video at 720p or 1080p, as a single shot or a short multi-shot sequence.
Kling v3
Kuaishou
Generate 3-15 second Kling VIDEO 3.0 clips from text or first and last frames at 720p or 1080p, with optional native audio.
Kling v3 Omni
Kuaishou
Combine up to 7 reference images, or first and last frames, into one Kling VIDEO 3.0 Omni clip at 720p or 1080p.
Seedance 2.0 Mini
ByteDance
Create 4-15 second 480p or 720p videos with audio from text or first and last frames using ByteDance Seedance 2.0 Mini.
PixVerse V6
PixVerse
Generate 1-15 second PixVerse V6 videos from text, one image, a first/last-frame pair, or up to 7 references at 360p to 1080p.
Grok Imagine Video 1.5
xAI
Generate 6-15 second xAI Grok Imagine Video 1.5 clips from text or up to 7 reference images at 480p or 720p.
Gemini Omni Flash
Generate 4-10 second Google Gemini Omni Flash videos from text, a first frame, or reference images at 720p, 1080p, or 4K, priced per video.
One task workflow, from request to result
Create a server-side API key, submit the supported inputs for your chosen model, and keep the returned task ID to retrieve the result. Model pages link to the exact request contract.
1. Create an API key
Sign in and create a key in the dashboard. Set WIZZX_API_KEY in your server environment; never expose it in browser code.
2. Submit a task
Send a POST request to the model endpoint. A successful submission returns data.task_id; keep that ID before polling. Submission is not generation completion.
3. Retrieve the result
Replace YOUR_TASK_ID with the returned ID and query /api/v1/task/status. Wait for SUCCEEDED and read the output URLs. Stop on FAILED or REVIEW_REQUIRED; do not automatically resubmit an uncertain task.