RunwayML Act Two is an advanced video generation API that animates characters using driving performance videos combined with character references. It enables efficient creation of high-quality short videos with a transparent, credit-based pricing system, making it accessible for developers and creators in creative and production workflows.
Vs. Pika Labs: Act Two's minimal 3-second video unit and transparent credit pricing make it better suited for rapid, budget-conscious prototyping, whereas Pika Labs may offer more customization for advanced workflows but at a higher price and computational requirement.
Vs. Kaiber: While Kaiber is recognized for its broader video transformation and style transfer capabilities, Act Two stands out by offering high-quality animated short videos with minimal compute needs, ideal for developers seeking straightforward deployment and predictable costs.
Vs. Sora: While Sora excels in delivering premium visual effects and extended scene generation, RunwayML Act Two stands out by providing immediate, cost-effective results for short-form animated videos, ideal for developers and content creators who value speed and affordability over advanced cinematic capabilities.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "runway/act_two", "prompt": "A serene timelapse of clouds over a mountain range" }, ).json() gid = job["id"] while True: res = requests.get(f"https://api.aimlapi.com/v2/video/generations?generation_id={gid}", headers=headers).json() if res.get("status") in ("completed", "error"): break time.sleep(5) print(res["video"]["url"])
const headers = { Authorization: `Bearer ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "runway/act_two", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${job.id}`, { headers })).json(); } while (!["completed", "error"].includes(res.status)); console.log(res.video.url);
# submit the generation — the response contains the job "id" curl -X POST https://api.aimlapi.com/v2/video/generations \ -H "Authorization: Bearer $AIMLAPI_KEY" \ -H "Content-Type: application/json" \ -d '{"model":"runway/act_two","prompt":"A serene timelapse of clouds over a mountain range"}' # then poll until status is "completed" — video.url holds the result curl "https://api.aimlapi.com/v2/video/generations?generation_id={id}" -H "Authorization: Bearer $AIMLAPI_KEY"
OpenAI-compatible — swap the base URL and it works with your existing SDK.
| Type | Price |
|---|---|
| Output | |
| Model | Input | Output | Context | Best for |
|---|---|---|---|---|
Runway Act Two This page | Video generation |
Runway Act Two takes image, text, video as input and returns video.
Runway Act Two became available on December 4, 2025.
Runway Act Two is priced at $0.065 / sec.
Runway Act Two is billed per generation — a fixed charge per output rather than by prompt length.
Yes, Runway Act Two accepts image input as well as a text prompt.
Runway Act Two was built by Runway.
Send a request to v2/generate/video/runway/generation with runway/act_two as the model id.
Yes. Runway Act Two is served through AI/ML API, so the same key and endpoint format used for other models applies.
It generates expressive, full-body performance videos by transferring the motion from a driving video onto a subject.
-min.webp){kind=small}
