Sora 2 Pro is OpenAI's flagship video generation model, released 2026-03, built for production-quality output with physics-accurate motion and synchronized audio. It maintains world-state persistence across shots, so objects and spatial relationships stay consistent through multi-shot sequences. The model supports text-to-video and image-to-video, and includes C2PA provenance metadata and watermarking for content safety.
Capabilities
Channels
Same weights on every channel. Requests route to the cheapest healthy one; the channel used is printed on each billing line.
Video pricing
Billed per second of generated video. The rate depends on the output resolution, and on whether audio is generated with it.
- Duration
- 4–20s
- Aspect ratios
- 16:9 · 9:16
- Audio generation
- Yes
Quick Start
import os from openai import OpenAI client = OpenAI( base_url="https://api.mirapi.ai/v1", # changed api_key=os.environ["MIRAPI_API_KEY"], # changed ) resp = client.chat.completions.create( model="openai/sora-2-pro", messages=[{"role": "user", "content": "Hello"}], )
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.mirapi.ai/v1", // changed apiKey: process.env.MIRAPI_API_KEY, // changed }); const res = await client.chat.completions.create({ model: "openai/sora-2-pro", messages: [{ role: "user", content: "Hello" }], });
curl https://api.mirapi.ai/v1/chat/completions \ -H "Authorization: Bearer $MIRAPI_API_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "openai/sora-2-pro", "messages": [{"role": "user", "content": "Hello"}] }'
Links
1M free tokens to start · no card · OpenAI-compatible, one base_url change