Sora 2 API
OpenAI Sora 2 — state-of-the-art text-to-video and image-to-video with realistic visuals, accurate physics, synchronized audio, and strong steerability. Standard and Pro tiers, plus a Characters endpoint for reusable character IDs across generations.
Text-to-video and image-to-video at Standard and Pro quality tiers. Pro variants emphasize higher fidelity, sharper realism, and greater steerability. The Characters endpoint creates reusable character IDs from video references for consistent appearance across Sora 2 generations.
About the Sora 2 API
What Sora 2 does, how it fits in the OpenAI model lineup, and why teams reach for it.
Sora 2 is a video generation model from OpenAI, available through the WaveSpeedAI REST API. OpenAI Sora 2 — state-of-the-art text-to-video and image-to-video with realistic visuals, accurate physics, synchronized audio, and strong steerability. Standard and Pro tiers, plus a Characters endpoint for reusable character IDs across generations.
Text-to-video and image-to-video at Standard and Pro quality tiers. Pro variants emphasize higher fidelity, sharper realism, and greater steerability. The Characters endpoint creates reusable character IDs from video references for consistent appearance across Sora 2 generations.
The Sora 2 family on WaveSpeedAI ships 7 REST endpoints covering Video-To-Text, Image-To-Video, Text-To-Video workflows. Each variant carries its own pricing, parameter knobs, and example outputs — pick the one that matches your input modality and production constraints, or call several from the same API key to compose multi-step pipelines.
Run Sora 2 through the same API key, billing account, and rate-limit envelope you use for the other 1,000+ AI models on WaveSpeedAI. No separate vendor setup, no per-provider SDKs, no per-vendor rate-limit envelopes — one integration covers everything from text-to-image and text-to-video through audio synthesis, 3D generation, upscaling, and editing.
All Sora 2 API endpoints
7 endpoints available now on WaveSpeedAI — pick the variant that matches your workflow.
Characters
OpenAI Sora 2 Characters creates reusable character IDs from video references for consistent character appearance across Sora 2 generations. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Image To Video
OpenAI Sora 2 Pro Image-to-Video creates physics-aware, realistic videos from reference images with synchronized audio and strong steerability. Supports 720p and 1080p resolutions with durations up to 20 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Text To Video
OpenAI Sora 2 Pro is a state-of-the-art text-to-video model with realistic physics, synchronized audio, and strong steerability. Supports multiple resolutions up to 1080p and durations up to 20 seconds. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Text To Video Pro
OpenAI Sora 2 Text-to-Video Pro creates high-fidelity videos with synchronized audio, realistic physics, and enhanced steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Text To Video
OpenAI Sora 2 is a state-of-the-art text-to-video model with realistic visuals, accurate physics, synchronized audio, and strong steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Image To Video Pro
OpenAI Sora 2 Image-to-Video Pro creates physics-aware, realistic videos with synchronized audio and greater steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
Image To Video
OpenAI Sora 2 generates realistic image-to-video content with synchronized audio, improved physics, sharper realism and steerability. Ready-to-use REST inference API, best performance, no coldstarts, affordable pricing.
See Sora 2 in action
Real outputs generated by the Sora 2 API. Hover any video to preview, click to open the full-size viewer.
How to use the Sora 2 API
Four steps from signup to a finished generation. Full Python, Node.js, and cURL examples are in the API section below.
- 1
Get an API key
Sign up for a WaveSpeedAI account and copy your API key from the dashboard. New accounts come with free starter credits — enough to run the playground a few dozen times before billing kicks in.
- 2
Submit a prediction
POST your input as JSON to https://api.wavespeed.ai/api/v3/openai/sora-2/text-to-video. The endpoint returns a prediction id immediately — generations are async so you don't hold an open connection during inference.
- 3
Poll for completion
GET https://api.wavespeed.ai/api/v3/predictions/{request_id}/result every 1-2 seconds. The response includes a status field; keep polling until it flips from"queued" or"processing" to"completed".
- 4
Read the output URL
Once status is"completed", read the URL from data.outputs[0]. The URL points to your generated media on the WaveSpeedAI CDN — image, video, audio, or 3D file depending on the Sora 2 variant you called.
What you can build with Sora 2
Common workflows developers and creators use the Sora 2 API for.
Text-to-video with synchronized audio
openai/sora-2/text-to-video generates realistic videos from text prompts with synchronized audio, accurate physics, and strong steerability — OpenAI's headline Sora 2 capability for greenfield creative briefs.
Image-to-video with physics-aware motion
openai/sora-2/image-to-video animates a reference still into a realistic video with synchronized audio and improved physics. Useful when the starting composition is locked and motion must respect the source image.
Pro tier for delivery-grade output
openai/sora-2/text-to-video-pro and image-to-video-pro create high-fidelity videos with synchronized audio, realistic physics, and enhanced steerability — the Pro tier when Standard output isn't sharp enough for delivery.
Reusable character IDs
openai/sora-2/characters creates reusable character IDs from video references so the same character appearance carries across multiple Sora 2 generations — useful for serialized content, brand mascots, and recurring cast members.
Steerability for precise creative control
Catalog emphasizes "strong steerability" and "greater steerability" on Pro variants. Write prompts with explicit camera, lighting, and action language — Sora 2 responds well to structured creative direction.
Physics-aware scenes
Catalog claim: "accurate physics" and "physics-aware" output on both text-to-video and image-to-video. Useful for product demos, sports motion, and scenes where object interaction must look physically plausible.
Tips for prompting Sora 2
Practical advice for getting better outputs from Sora 2 — drawn from the patterns that work across video models in production pipelines.
Use Pro tier for delivery, Standard for iteration
Same prompt format across Standard and Pro — switch the endpoint URL only. Iterate on Standard to find direction, switch to Pro when physics accuracy and steerability need to hold at delivery quality.
Create character IDs for recurring cast
openai/sora-2/characters builds reusable IDs from video references. Train once, reference the ID in subsequent text-to-video and image-to-video calls — faster than re-uploading reference clips every generation.
Describe physics and interaction explicitly
Catalog emphasizes accurate physics. Spell out how objects interact — pouring, bouncing, colliding, fabric draping — rather than assuming the model infers physical behavior from subject alone.
Anchor steerability with structured prompts
Subject + scene + camera + lighting + action in one prompt. Sora 2's steerability claim maps best to structured creative briefs, not one-word prompts.
Pair image-to-video with a strong key still
Start from a high-quality reference image when composition matters. Sora 2's image-to-video preserves the starting frame while adding physics-aware motion and synchronized audio.
Sora 2 API pricing
Pricing is per-output. The final charge scales with the parameters you set in each variant's playground (resolution, duration, output count, references).
| Endpoint | Type | Starting price |
|---|---|---|
| openai/sora-2/characters | video-to-text | $0.001 |
| openai/sora-2-pro/image-to-video | image-to-video | $1.20 |
| openai/sora-2-pro/text-to-video | text-to-video | $1.20 |
| openai/sora-2/text-to-video-pro | text-to-video | $1.20 |
| openai/sora-2/text-to-video | text-to-video | $0.40 |
| openai/sora-2/image-to-video-pro | image-to-video | $1.20 |
| openai/sora-2/image-to-video | image-to-video | $0.40 |
Call the Sora 2 API
Sign up for an API key at wavespeed.ai/accesskey, then submit a prediction via REST. The playground generates ready-to-paste samples for any combination of inputs.
HTTP example
# 1. Submit a prediction
curl -X POST "https://api.wavespeed.ai/api/v3/openai/sora-2/text-to-video" \
-H "Content-Type: application/json" \
-H "Authorization: Bearer $WAVESPEED_API_KEY" \
-d '{}'
# 2. Poll the result until status = "completed"
curl -X GET "https://api.wavespeed.ai/api/v3/predictions/{request_id}/result" \
-H "Authorization: Bearer $WAVESPEED_API_KEY"
# Read the output URL from data.outputs[0].Node.js example
// npm install wavespeed
const WaveSpeed = require('wavespeed');
const client = new WaveSpeed(); // reads WAVESPEED_API_KEY
const result = await client.run("openai/sora-2/text-to-video", {});
console.log(result.outputs[0]); // → URL of the generated outputPython example
# pip install wavespeed
import wavespeed
output = wavespeed.run(
"openai/sora-2/text-to-video",
{}
)
print(output["outputs"][0]) # → URL of the generated outputSora 2 vs alternatives
When to pick Sora 2 over similar models on WaveSpeedAI.
Sora 2 vs Veo 3.1
Veo 3.1 ships three pricing tiers (Standard / Fast / Lite) with reference-to-video and start-end interpolation. Sora 2 emphasizes physics accuracy and steerability with a dedicated Characters endpoint for cross-generation identity — different feature surfaces at comparable premium price points.
Sora 2 vs Seedance 2.0
Seedance 2.0 ships native audio across every variant plus video-edit and video-extend at lower cost. Sora 2 is positioned around OpenAI's photorealism and physics priors with the Characters workflow for recurring identity.
Sora 2 vs Kling 3.0
Kling 3.0 covers Standard, Pro, and 4K tiers with motion-control as a sub-endpoint. Sora 2 stays focused on text-to-video and image-to-video with Pro quality tiers and the Characters endpoint — no motion-control, but strong physics and steerability claims.
Sora 2 API — Frequently asked questions
Pricing, license, integration — common questions about running Sora 2 on WaveSpeedAI.
What is the Sora 2 API?
Sora 2 is a OpenAI video generation model exposed as a REST API on WaveSpeedAI. OpenAI Sora 2 — state-of-the-art text-to-video and image-to-video with realistic visuals, accurate physics, synchronized audio, and strong steerability. Standard and Pro tiers, plus a Characters endpoint for reusable character IDs across generations. You can call it programmatically or try it from the playground linked above.
How do I call the Sora 2 API?
Sign up for a WaveSpeedAI account, copy your API key from /accesskey, then POST to https://api.wavespeed.ai/api/v3/openai/sora-2/text-to-video with your input as JSON. The endpoint returns a prediction id; poll the prediction endpoint until status flips to "completed", then read the output URL from data.outputs[0]. Full Python / Node.js / cURL examples are above.
How much does the Sora 2 API cost?
Sora 2 starts at $0.001 per run. The exact cost scales with the parameters you set (resolution, duration, output count, references). The live cost preview next to the Generate button in the playground shows the exact price for your current input.
Which Sora 2 variants are available?
WaveSpeedAI hosts 7 Sora 2 endpoints: openai/sora-2/characters, openai/sora-2-pro/image-to-video, openai/sora-2-pro/text-to-video, openai/sora-2/text-to-video-pro, openai/sora-2/text-to-video, openai/sora-2/image-to-video-pro, openai/sora-2/image-to-video. Each variant has its own playground page and pricing.
Can I use Sora 2 outputs commercially?
Commercial usage rights follow the OpenAI model license. Most OpenAI models permit commercial output use; see each model's playground page for the specific license summary, and WaveSpeedAI's Terms of Service for platform-level conditions.
Why use Sora 2 on WaveSpeedAI instead of going direct?
One API key + one billing account across Sora 2 AND 1,000+ other AI models from other providers. No per-vendor SDK setup, no separate rate-limit envelopes, no rewrite-per-vendor integration code. Pricing is typically at parity with or below OpenAI's direct API.
About OpenAI
The team behind Sora 2 and the broader OpenAI model lineup on WaveSpeedAI.
OpenAI is the lab behind ChatGPT, GPT-4 and GPT-5, DALL·E, Sora, and Whisper. Its image and video models are deployed widely across consumer and enterprise applications, with a focus on instruction-following, photorealism, and conservative safety guardrails. The image API is a frequent pick for marketing and editorial use cases that need strict commercial-use clarity.
Start building with Sora 2 on WaveSpeedAI
Free starter credits on signup. One API key across 1,000+ AI models from OpenAI and every other provider.