Sora 2 API
by OpenAI
OpenAI's video model, built for realism.
OpenAI's video model through one unified API. Realistic clips from 4 to 15 seconds in 16:9 or 9:16, from a text prompt or a start image, with synchronized sound and dialogue. A single REST endpoint, async jobs, and webhooks.
- 15s
- Max clip length
- 2
- Aspect ratios
- ~180s
- Avg. generation
- 50 credits
- From
Playground
Try Sora 2 right here.
Capabilities
What's new in Sora 2.
Physics that hold up
Sora 2 models momentum, fluids, and collisions convincingly, the action shots that break other models are exactly where it shines.
Dialogue and synced sound
Speech, effects, and ambience are co-generated and matched to the scene, so talking scenes arrive with usable, lip-synced audio.
Start from a still
Pass a start image to lock composition and identity for the opening frame, the dependable way to keep a product or character on-model.
Flat per-clip pricing
From 50 credits ($0.50) per clip depending on duration. Draft here, then re-run the winning prompt on Sora 2 Pro for the final master.
Feed-native formats
Native 16:9 and 9:16 output from 4 to 15 seconds covers both widescreen and vertical placements without cropping.
Showcase
See what Sora 2 can create.
Real outputs generated with Sora 2 on Apiframe, each with the prompt behind it.
Two commuters arguing playfully on a subway platform as a train arrives, natural dialogue, steam from the tunnels, realistic physics on coats and papers in the wind.
A golden retriever leaping into a lake in slow motion, water spray backlit by the sun, realistic splash physics, handheld documentary feel.
Water dripping from a subway ceiling into a puddle on tile, slow motion splash physics, a violin case on the floor, warm practical light, realistic fluids.
Vertical handheld of a street musician playing violin in a subway station, commuters passing behind, natural reverb, warm light.
Handheld footage of a street musician playing violin in a tiled subway station, commuters passing, natural reverb off the tiles, warm practical light, realistic physics on the bow and strings.
Pricing
Simple per-generation pricing.
50–188 credits per generation ≈ $0.50–$1.88
The rate depends on the resolution and options you pick.
- You only pay for successful generations. Failed jobs are refunded automatically.
- One credit balance across every model on Apiframe, no per-model plans.
- Start with free credits. No subscription required.
- Volume discounts on larger plans.
Specs
At a glance.
Comparison
Sora 2 vs Sora 2 Pro vs Veo 3.1
Sora 2 against its Pro tier and its closest rival on Apiframe. Pick per shot, same API key.
| Feature | Sora 2 | Sora 2 Pro | Veo 3.1 |
|---|---|---|---|
| Quality tier | Standard | Standard or HD | Up to 1080p |
| Max clip length | 15s | 15s | 8s |
| Image inputs | Start frame | Start frame | Start & end frames + 3 references |
| Price per clip | 50–188 credits (≈$0.50–$1.88) | 150–938 credits (≈$1.50–$9.38) | 100–400 credits (≈$1.00–$4.00) |
| Avg. generation | ~180s | ~240s | ~120s |
| Best for | Realistic physics and dialogue at a fair price | Final masters where fidelity wins | Filmic single shots with sound |
Specs reflect what each model supports on Apiframe today, from the live catalog.
Quickstart
How to call the Sora 2 API.
Send one POST /v2/videos/generate request with your API key. The call returns a jobId you can poll, or pass a webhook_url and the result is pushed to you the moment it's ready.
Swap sora-2 for any other model and nothing else changes.
const response = await fetch("https://api.apiframe.ai/v2/videos/generate", {
method: "POST",
headers: {
"X-API-Key": "afk_your_api_key_here",
"Content-Type": "application/json",
},
body: JSON.stringify({
"prompt": "a cinematic sunrise over a futuristic cityscape, smooth camera push-in",
"model": "sora-2",
"soraParams": {
"start_image": "https://example.com/input.jpg"
}
}),
});
const { jobId } = await response.json();
console.log(jobId); Input schema
Every field Sora 2 accepts, with types and defaults. The full reference lives in the docs.
| Field | Type | Description |
|---|---|---|
| prompt required | string | Text description of what to generate. |
| model required | string | The model identifier for this endpoint. Default:"sora-2" · "sora-2" |
| soraParams.start_image | string (URL) | Image-to-video starting frame. |
Sora versions
Every Sora video model on Apiframe. Switch with one parameter.
Use cases
What teams build with Sora 2.
Realistic action & physics
Sora 2 models momentum, collisions, and fluids convincingly, the shots that break other models, like gymnastics or water, are where it earns its keep.
Social-native video
Native 16:9 and 9:16 output from 4 to 15 seconds, sized for feed and story placements, with flat per-clip pricing that keeps unit costs predictable.
Dialogue & synced sound
Sora 2 co-generates speech, effects, and ambience matched to the scene, so talking-head and dialogue-driven clips arrive with usable sound.
Image-anchored scenes
Start from a still to lock composition and identity, then let the model take the shot from there, the reliable way to keep a product or character on-model.
Reviews
9,800+ developers. One API.
Real Apiframe reviews from Trustpilot and G2.
Seamless experience, excellent support
Just created 6 videos and the experience has been seamless. Wanted to write a review for appreciation — the customer support has also been excellent. They helped me in some process I was stuck in.
Stable, easy image & video generation
I like that I can generate images and videos without complicated setup. It works stable and is easy to use even if you are not a big developer. It saves me time and makes the whole process much simpler.
Honestly the best AI API
They got every engine possible and it's great to have them all in one place.
Sora 2 questions
What teams ask before shipping with Sora 2. Everything else lives in the docs.
How long can a Sora 2 video be?
Choose 4, 8, 10, 12, or 15 seconds per generation, in 16:9 or 9:16. Longer pieces are built by generating consecutive shots and editing them together.
What does Sora 2 cost on Apiframe?
Flat per-clip pricing from 50 credits (≈$0.50) to 188 credits (≈$1.88) depending on duration. The higher-fidelity Sora 2 Pro tier starts at 150 credits (≈$1.50).
Does Sora 2 generate audio?
Yes. Sound effects, ambience, and dialogue are generated with the picture and synchronized to it, including lip-sync on speaking characters.
How is Sora 2 different from Sora 2 Pro?
Same model family, different quality tier. Pro renders at higher fidelity with an HD option and costs roughly 3× more per clip, most teams iterate on Sora 2 and master on Pro.
Do I need an OpenAI account?
No. You call one Apiframe REST endpoint with your Apiframe key, the provider relationship, queuing, and delivery are handled for you.
Related models
All video modelsFlux 3
by Black Forest Labs
Black Forest Labs' multimodal model — up to 20s of video with synchronized audio from text, images, or a clip.
View modelVeo 3.1
by Google
Google's flagship cinematic video model with audio.
View modelKling 3.0
by Kuaishou
Latest Kling — per-second pricing, optional audio.
View modelSeedance 2.5
by ByteDance
Next-gen ByteDance video — 30s single-pass clips, up to 50 multimodal references (30 images / 10 videos / 10 audio), native synced audio.
View model9,800+
developers & companies
Official partner of
Power your next AI product with Apiframe.
Instant access to 70+ media models through a single API. Start free and scale when you're ready.