OpenAI: Sora 2 Pro

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.

Modalities
inTextinImageoutVideo
Per second
$0.300720p
Resolution
720p · 1080p · 1024p
Duration
4–20s

Capabilities

Vision

Channels

Same weights on every channel. Requests route to the cheapest healthy one; the channel used is printed on each billing line.

Provider
Discount
Input /M
Output /M
Cache Read /M
Cache Create 5m /M
Cache Create 1h /M
Codexcheap
$0.00
$0.00
Defaultstable
$0.00
$0.00

Video pricing

Billed per second of generated video. The rate depends on the output resolution, and on whether audio is generated with it.

Resolution
Per second
720p
$0.300
1080p
$0.500
1024p
$0.500
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"}],
)
Wire Sora 2 Pro into your product

1M free tokens to start · no card · OpenAI-compatible, one base_url change

Start free