https://api.laozhang.ai/v1/chat/completions (API version v1).
Prerequisites
1
Get API Key
Log in to laozhang.ai console to obtain your API key
2
Configure Billing Mode
Edit token settings and choose one of the following billing modes (same price for both):
- Usage first (按量优先, recommended): can call both usage-based and per-call models; when a model has both prices, it’s billed by usage
- Per-call (按次计费): can call only per-call models
Legacy route update history
LaoZhang API launched the legacy Sora 2 route on October 1, 2025, before OpenAI released an official Sora 2 API.- 01/04 Added the Character Creation API to extract characters from videos and reuse them via @username ($0.01/call)
- 10/20 15-second models dropped from $0.25 to $0.15/call, with unified pricing for all models; added raw error logs
- 10/18 Added support for videos with the native Sora watermark (otherwise, watermarking followed the model output)
- 10/16 Restored 15-second models (sora_video2-15s and sora_video2-landscape-15s)
- 10/10 Added the sora-2-pro HD model, with HD 1080P and 15-second duration (Async API only)
- 10/07 Added Python example code; OpenAI launched the official sora-2 and sora-2-pro models
- 10/01 Integrated the Sora 2 legacy route API, supporting text-to-video and image-to-video
Sora 2 model features
OpenAI introduced Sora 2 with these features:- Synchronized audio and video generation
- More realistic physics
- Coherent narrative videos of 10–16 seconds
- Cameo: blends recorded clips of real people into AI scenes
- Remix: lets the community build on existing videos
Core Features
- Text-to-Video: Generate videos from pure text descriptions
- Image-to-Video: Supports reference images (up to 1 image)
- Character Creation: Extract characters from videos, reuse via @username
- Async API: Task queue approach for long-running tasks
- Multi-Spec Support: Horizontal and vertical orientation options
- Per-call billing: Charged only by generation count
Workflow
1
Configure API Key
Get an API key from the laozhang.ai console and set the token to Usage first or Per-call billing
2
Send Request
Call
/v1/chat/completions endpoint, specify model and prompt3
Real-time Progress
View task queue and generation progress through streaming output
4
Get Video
Obtain video link after generation completes (valid for 1 day)
5
Download & Save
Download video to local storage immediately
Price Update (10/20)15-second models dropped from $0.25 to $0.15/call. From then on, all base models cost $0.15/call regardless of duration or orientation. The HD model sora-2-pro ($0.8/call) was available only via the Async API. These are historical prices.
Supported Models
The prices below are historical prices from before the legacy route was retired.sora-2-pro was available only via the Async API.
Video Specifications
- Duration: 10 seconds or 15 seconds (selected via model name)
- Quality: 720P
- Orientation: Vertical or horizontal (selected via model name)
- Watermark: Determined by the model output
- Audio: Supports audio-video synchronization
API Method Selection
The legacy route recommended the Async API for production workloads and batch generation.Other legacy route docs
Sync API
Quick start with streaming output (for testing)
Async API
Task queue approach for long-running tasks
Character Creation
Extract characters, reuse via @username
Model Pricing
Model comparison and historical prices
Code Examples
View multi-language example code
FAQ
Common issues with the legacy route