Video Generation API: Free AI Video & Image API
Turn text into video in two simple steps: submit a task, poll its status, then grab the result. Free, no GPU, developer-friendly.
The Agnes open API (Base URL: https://apihub.agnes-ai.com) gives programmatic access to free video and image models. The standard flow is a POST to create a task, then polling until done, then reading video_url from the response. Authenticate with a Bearer token; the quota is 16 requests per minute with automatic exponential backoff on 429.
API Endpoints
| Method | Endpoint | Description |
|---|---|---|
| POST | /v1/videos | Create a video generation task. Body: model (agnes-video-v2.0), prompt, width/height, num_frames, frame_rate. Returns a task id. |
| GET | /agnesapi | Poll a video task by video_id; returns status (pending/completed/failed), progress, and video_url when done. |
| POST | /v1/images/generations | Create an image generation task with model agnes-image-2.1-flash, a prompt and a size. |
| GET | /v1/models | List the available text, image and video models with their model ids. |
API Features
Completely free, no GPU or credit card needed
One key for text, image and video models
Async tasks polled every ~30s (up to 15 minutes)
Prompts in Chinese and many other languages
Selectable resolution, frames and duration up to 720p
16 requests/min rate limit with automatic backoff
Quick Start Example
# Step 1 — create a video job
import requests, time
API_KEY = "your-api-key" # get it free at platform.agnes-ai.com
BASE = "https://apihub.agnes-ai.com"
headers = {"Authorization": f"Bearer {API_KEY}"}
resp = requests.post(f"{BASE}/v1/videos", headers=headers, json={
"model": "agnes-video-v2.0",
"prompt": "A white fox walking in a misty bamboo grove at dawn",
"width": 1152, "height": 768, # 16:9
"num_frames": 121, # ~5s @24fps
"frame_rate": 24,
})
resp.raise_for_status()
video_id = resp.json().get("video_id") or resp.json().get("task_id")
# Step 2 — poll the task until done
while True:
r = requests.get(f"{BASE}/agnesapi", headers=headers,
params={"video_id": video_id}).json()
if r["status"] == "completed":
print("Video URL:", r["video_url"]); break
if r["status"] == "failed":
raise RuntimeError(r.get("error", "generation failed"))
time.sleep(30)Agnes API lets any developer plug real AI video generation into an app for free. Call GET /v1/models to see current model ids, POST /v1/videos to submit a task, then poll to fetch the clip. Combined with the rate-limit notes above, it is enough to ship quickly.
Related Pages
Get a Free Agnes AI API Key — 3-Minute Setup | Free AI Video Guide
Agnes AI API keys are completely free: full steps to register, create and copy, three configuration methods (Web UI / env var / API), and 401 troubleshooting.
Agnes Self-Hosting Guide — Docker, npm, AI Agent | Free AI Video Guide
Run the free open-source AI video generator on your own computer or server: start.sh manual deployment, one-command Docker, npm CLI, AI Agent — complete commands and requirements.
FAQ — AI Video Generator Questions & Answers | Agnes Video
Everything people usually ask about Agnes Video Generator: how to use Agnes AI's free video models, whether you really can skip the high-end GPU, what's free and what's limited, and how this compares to paid tools.
Simple Video Prompt Examples — Text-to-Video Prompts | Free AI Video
Ready-made prompts for Simple Video mode: lakeside sunset, food close-ups, and neon night streets — 3 copy-paste examples that generate short AI videos instantly.
API Contract & Conventions
Endpoints, auth, and parameters here follow the Agnes AI Open API, with reference to mainstream API conventions.
- Agnes AI Open API — 视频 / 图片生成接口Agnes AI · apihub.agnes-ai.com (2026)
The request/response contracts of all endpoints (/v1/videos, status polling, etc.) follow the Agnes Open API docs.
- OpenAI API Reference — REST 接口规范OpenAI · OpenAI Docs (2025)
Conventions like Bearer auth and REST-style design reference industry standards such as the OpenAI API Reference.
- Artificial Intelligence Index Report 2025Stanford HAI · Stanford AI Index 2025 (2025)
Stanford AI Index 2025 documents the explosive growth of the AI API economy, validating API documentation standardization as critical industry infrastructure.
- The Economic Potential of Generative AI: The Next Powerhouse of Productivity and Growth?McKinsey & Company · McKinsey Global Institute (2023)
McKinsey's report estimates the economic value of API-driven AI services in enterprise integration, providing developers a business case for API-based integration.
Why you can trust this
Written by a practicing developer and cross-checked against authoritative primary sources such as arXiv papers, vendor technical reports, and the Stanford AI Index.
SandGrid@lcy362
Author of Agnes Video Generator · Full-stack Developer
Independent developer and author of Agnes Video Generator, an open-source (MIT) AI video generation tool built on Agnes AI's free video models. Has helped 1,000+ creators produce AI videos at zero cost. Focused on making video generation models accessible and production-ready; content is based on hands-on practice and primary research.
View on GitHubLast updated:2026-08-21
Ready to Start Creating?
"Making world-class AI belong to everyone." — Bruce Yang. It's completely free, no credit card, and you won't need a high-end GPU. Your first AI video starts at zero cost. Want to use Agnes AI's free video models? This is the easiest way in.
Clone the GitHub repo and launch in 2 minutes