Sora 2 is OpenAI's video generation model that produces short clips together with synchronized audio: dialogue, sound effects, and music generated alongside the visuals.
- Input
- text image
- Output
- video
- Price
- $0.1/s
Price in context
Where the price sits among 5 comparable models
The bar shows how this model’s price compares with every other model of the same kind on Synthorai. The cheapest and the most expensive are named at each end. These are base rates; batch, region and cache-write discounts are on the pricing page.
Specs & limits
Video
| Resolution | 720p |
|---|---|
| Clip length | 4-12 s A continuous range, not a fixed set. |
| Frame rate | 24 fps |
| Aspect ratios | 16:9 · 9:16 |
| Video inputs | text-to-video · image-to-video (single reference image) |
| Native audio | Yes, generates sound |
| Format | .mp4 |
Model
| Modalities | text + image → video |
|---|
- OpenAI's deprecations page (announced 2026-03-24) lists this model for removal from the API on 2026-09-24 with no recommended replacement
- the pricing page carries no deprecation notice, so the two vendor pages disagree - the deprecations page is the one that names a date. OpenAI's Sora 2 video model, which generates video together with synchronized audio (dialogue, sound effects, and music). Synthorai serves it via the async /v1/videos job API at 720p, 24 fps, 4-12 s, 16:9 or 9:16, and bills per output second
One prompt, measured through the gateway
Sora 2
Model returned 720×1280 Length 4s latency 68 s
One prompt, one request per model, no retries and no cherry-picking - the first result each model returned. Neither size nor duration was pinned: each model used its own default, because a request shaped to fit all of them would flatter none. Files here are re-encoded for the web, so judge composition and prompt adherence, not compression.
Use Sora 2 in 30 seconds
Asynchronous job API: create a task and poll it, or hold the request open with Prefer: wait. POST /v1/videos
import time
import requests
BASE = "https://synthorai.io/v1"
HEADERS = {"Authorization": "Bearer sk-syn-..."}
# 1) create the video generation job (POST /v1/videos)
task = requests.post(
f"{BASE}/videos",
headers=HEADERS,
json={
"model": "sora-2",
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5,
},
).json()
# 2) poll the job until it reaches a terminal state
while task["status"] in ("queued", "in_progress"):
time.sleep(5)
task = requests.get(f"{BASE}/videos/{task['id']}", headers=HEADERS).json()
# 3) completed → signed video URL (valid ~24h - download and store it promptly)
if task["status"] == "completed":
print(task["data"][0]["url"])
else:
print(task["error"])const HEADERS = {
Authorization: "Bearer sk-syn-...",
"Content-Type": "application/json",
};
interface VideoTask {
id: string;
status: "queued" | "in_progress" | "completed" | "failed" | "cancelled";
data?: Array<{ url: string }>;
error?: { code: string; message: string };
}
// 1) create the video generation job (POST /v1/videos)
const created = await fetch("https://synthorai.io/v1/videos", {
method: "POST",
headers: HEADERS,
body: JSON.stringify({
model: "sora-2",
prompt: "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
resolution: "720p",
duration: 5,
}),
});
let task = (await created.json()) as VideoTask;
// 2) poll the job until it reaches a terminal state
while (task.status === "queued" || task.status === "in_progress") {
await new Promise((r) => setTimeout(r, 5000));
const res = await fetch(`https://synthorai.io/v1/videos/${task.id}`, { headers: HEADERS });
task = (await res.json()) as VideoTask;
}
// 3) completed → signed video URL (valid ~24h — download and store it promptly)
if (task.status === "completed") console.log(task.data?.[0]?.url);
else console.error(task.error);# Create the job; "Prefer: wait" holds the request up to 60s and returns the
# completed task when generation finishes in time (else the queued task).
curl https://synthorai.io/v1/videos \
-H "Authorization: Bearer sk-syn-..." \
-H "Content-Type: application/json" \
-H "Prefer: wait=60" \
-d '{
"model": "sora-2",
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5
}'
# Still queued / in_progress? Poll until completed → data[0].url (valid ~24h).
curl https://synthorai.io/v1/videos/vid_9f2e8c1a4b7d \
-H "Authorization: Bearer sk-syn-..."package main
import (
"bytes"
"encoding/json"
"fmt"
"net/http"
"time"
)
const base = "https://synthorai.io/v1"
type videoTask struct {
ID string `json:"id"`
Status string `json:"status"`
Data []struct {
URL string `json:"url"`
} `json:"data"`
}
func call(method, url string, body []byte) (t videoTask) {
req, _ := http.NewRequest(method, url, bytes.NewReader(body))
req.Header.Set("Authorization", "Bearer sk-syn-...")
req.Header.Set("Content-Type", "application/json")
resp, _ := http.DefaultClient.Do(req)
defer resp.Body.Close()
json.NewDecoder(resp.Body).Decode(&t)
return t
}
func main() {
// 1) create the video generation job (POST /v1/videos)
payload, _ := json.Marshal(map[string]any{
"model": "sora-2",
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p",
"duration": 5,
})
task := call("POST", base+"/videos", payload)
// 2) poll the job until it reaches a terminal state
for task.Status == "queued" || task.Status == "in_progress" {
time.Sleep(5 * time.Second)
task = call("GET", base+"/videos/"+task.ID, nil)
}
// 3) completed → signed video URL (valid ~24h — download and store promptly)
if task.Status == "completed" {
fmt.Println(task.Data[0].URL)
}
}import java.net.URI;
import java.net.http.HttpClient;
import java.net.http.HttpRequest;
import java.net.http.HttpResponse;
// JDK built-in HttpClient — no extra dependency needed.
HttpClient http = HttpClient.newHttpClient();
// 1) create the job; "Prefer: wait=60" holds the request up to 60s and
// returns the completed task when generation finishes in time
HttpRequest create = HttpRequest.newBuilder(URI.create("https://synthorai.io/v1/videos"))
.header("Authorization", "Bearer sk-syn-...")
.header("Content-Type", "application/json")
.header("Prefer", "wait=60")
.POST(HttpRequest.BodyPublishers.ofString("""
{"model": "sora-2",
"prompt": "a watercolor lighthouse at dawn, waves rolling in, camera pulling back",
"resolution": "720p", "duration": 5}"""))
.build();
String task = http.send(create, HttpResponse.BodyHandlers.ofString()).body();
System.out.println(task); // {"id":"vid_…","status":…} — completed → data[0].url
// 2) still queued / in_progress? Poll GET https://synthorai.io/v1/videos/{id} until the
// status turns completed, then download data[0].url (valid ~24h).About Sora 2
- It creates video from a text prompt or from a reference image, in a controllable, physically grounded style.
- OpenAI positions this tier for speed and flexibility, calling it the model for the exploration phase, when you are experimenting with tone, structure, or visual style and want quick feedback rather than perfect fidelity; the Pro tier is the documented choice for production-quality output.
- A reference image has to match the target video's size and be supplied as JPEG, PNG, or WebP.
- Beyond a single generation, OpenAI documents an extension flow that stitches additional footage onto a finished clip and an edits endpoint for targeted adjustments without regenerating everything, plus reusable characters for keeping a subject consistent across clips, capped at two per video.
- Content rules are strict and enforced upstream: real people including public figures cannot be generated, input images containing human faces are rejected, copyrighted characters and music are refused, and output must be suitable for a general audience.
- Synthorai serves Sora 2 through the asynchronous /v1/videos job API at 720p, 24 fps, 4 to 12 seconds, in 16:9 or 9:16, and bills per output second.
- Create a task, then poll it (or hold the request open with Prefer: wait) until the signed video URL is ready.
FAQ
Is the Sora 2 API free to try?
Yes: new accounts get 10 trial calls and up to $1 in free credit, no card required. That's enough to try Sora 2 against your real workload before adding a payment method.
What is Sora 2 best at?
OpenAI video model with synchronized audio; text-to-video and image-to-video; 720p, 24 fps, 4-12 seconds. See the About section for the full picture from the vendor's own release notes.
How much does Sora 2 cost?
Sora 2 costs $0.1 per second of generated video on Synthorai. Only successful generations are billed: pay-as-you-go, no platform markup, no subscription.
How do I generate videos with the Sora 2 API?
POST to /v1/videos on Synthorai with model="sora-2" to create an asynchronous job, then poll the task (or hold the request open with a Prefer: wait header) until the video URL is ready. No vendor SDK is needed.
How do I get access to Sora 2?
Point your existing OpenAI SDK at base_url="https://synthorai.io/v1", set model="sora-2", and you're done. One API key covers every model on the gateway.
Related models
Compare
Every value on this page is transcribed from the vendor's own documentation, linked above, and carries the date it was checked. Prices are compared across the catalogue; specification values that vendors define differently are shown with the difference stated rather than charted. Nothing here is measured by us, and nothing is scored.