Ray Flash 2 is a cutting-edge video generation model built on Luma’s multi-modal architecture. The model offers accelerated workflows with rapid iterations, real-time previews, and high-fidelity output, making it ideal for professional content creators and developers seeking fast, detailed, and realistic video synthesis.
vs Luma Ray 2: Ray Flash 2 is a distilled, faster variant of Luma Ray 2, offering up to three times faster video generation and costing less while retaining strong video realism. Ray 2 provides higher fidelity and supports more complex animations, but at slower speeds and higher resource usage.
vs Luma Ray 1.6: Compared to Luma Ray 1.6, Ray Flash 2 offers improved speed, much higher resolution (up to 720p), and better motion coherence. Ray 1.6 produces shorter, lower-resolution videos with less natural motion.
vs Synthesia: Ray Flash 2 excels in photorealistic video content creation with coherent scene dynamics, while Synthesia focuses on real-time avatar animations and lip-sync for interactive video content. Ray Flash 2 is more suitable for cinematic and complex video generation.
import requests, time headers = {"Authorization": "Bearer " + AIMLAPI_KEY} job = requests.post( "https://api.aimlapi.com/v2/video/generations", headers=headers, json={ "model": "luma/ray-flash-2", "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 ${process.env.AIMLAPI_KEY}`, "Content-Type": "application/json", }; const job = await (await fetch("https://api.aimlapi.com/v2/video/generations", { method: "POST", headers, body: JSON.stringify({ "model": "luma/ray-flash-2", "prompt": "A serene timelapse of clouds over a mountain range" }), })).json(); let res; do { await new Promise((r) => setTimeout(r, 5000)); res = await (await fetch(`https://api.aimlapi.com/v2/video/generations?generation_id=${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":"luma/ray-flash-2","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 |
|---|---|---|---|---|
Ray Flash 2 This page | Video generation |
Ray Flash 2 takes image, text as input and returns video.
Ray Flash 2 became available on December 2, 2025.
Ray Flash 2 is priced at $0.002 / 1M px.
Ray Flash 2 is billed per generation — a fixed charge per output rather than by prompt length.
Yes, Ray Flash 2 accepts image input as well as a text prompt.
Ray Flash 2 was built by Luma AI.
Send a request to v2/video/generations with luma/ray-flash-2 as the model id.
Yes. Ray Flash 2 is served through AI/ML API, so the same key and endpoint format used for other models applies.
Ray Flash 2 is a video generation model from Luma AI, designed to be faster and more cost-effective than other Luma models.
-min.webp){kind=small}
