OpenAI● Available
OpenAI Sora 2 Pro API
Sora 2 Pro 高质量视频生成模型，支持文生视频和单图参考生成。
Text to videoImage to video 720x12801280x7201024x17921792x1024 4s / 8s / 12s
Model pricing
Pricing follows the current production configuration and the billing dimensions supported by each route.
| Route | Price | Billing rule |
|---|---|---|
| 720x1280 / 1280x720 | 12 秒 $3.355/request4 秒 $1.1187/request8 秒 $2.2363/request | 按时长固定计费 |
| 1024x1792 / 1792x1024 | 12 秒 $5.5924/request4 秒 $1.8645/request8 秒 $3.7279/request | 按时长固定计费 |
Model information
Only provider-documented routes, capabilities, and limits implemented by this gateway are listed.
sora-2-pro
- Limits
- —
- Duration
- 4s / 8s / 12s
sora-2-pro
- Limits
- Images 1
- Duration
- 4s / 8s / 12s
Main parameters
Parameters come from structured model configuration; unsupported or unconfigured fields are omitted.
modelstringSubmodel ID
Default:sora-2-pro / sora-2-propromptstringSora 2 Pro 高质量视频生成模型，支持文生视频和单图参考生成。
Default:RequireddurationintegerOutput video seconds
Default:4s / 8s / 12ssizeenumCurrent billing
Default:720x1280 / 1280x720 / 1024x1792 / 1792x1024image_urlsarrayImage to video: 1
Default:Varies by routeCapabilities and usage guidance
Key features
- Text to video · sora-2-pro
- Image to video · sora-2-pro
- 720x1280 / 1280x720 / 1024x1792 / 1792x1024 output
- 4s / 8s / 12s Duration
- Generated audio output
- Audio-capable workflow
Limits
- Image to video: Images 1
- Capability source: https://evolink.ai/zh/sora-2
Typical use cases
Text to video
OpenAI Sora 2 Pro Text to video API workflow.
Image to video
OpenAI Sora 2 Pro Image to video API workflow.
Frequently asked questions
Which video workflows does OpenAI Sora 2 Pro support?
Text to video、Image to video
What video durations does OpenAI Sora 2 Pro support?
4s / 8s / 12s
Which output resolutions or sizes does OpenAI Sora 2 Pro support?
720x1280、1280x720、1024x1792、1792x1024
Models in this family
Explore other available variants from the same model family.
OpenAI Sora 2 Pro
OpenAI Sora 2
View model →Other video models
Explore more models available through the unified asynchronous video task API.
