What is Ray Flash 2 AI model?

Ray Flash 2 is a high-speed, cost-efficient language model optimized for fast inference and low latency, making it ideal for applications requiring quick responses and high throughput.

What are the main advantages of Ray Flash 2?

Ray Flash 2 offers exceptional speed, very competitive pricing, and reliable performance for general-purpose language tasks with a 128K context window.

How much does Ray Flash 2 cost?

Ray Flash 2 is very cost-effective with pricing at $0.10 per million input tokens and $0.40 per million output tokens, making it one of the most affordable options available.

What is the context window size for Ray Flash 2?

Ray Flash 2 features a 128K token context window, allowing it to handle extensive conversations and process long documents while maintaining context.

How do I access the Ray Flash 2 API?

Access through OpenAI-compatible API endpoints at https://api.aimlapi.com/v1/chat/completions using your AIMLAPI key with the model parameter 'ray-flash-2'.

What types of applications is Ray Flash 2 best suited for?

Ray Flash 2 is ideal for chat applications, content generation, customer support, data processing, and any use case requiring fast, cost-effective language processing.

How fast is Ray Flash 2 compared to other models?

Ray Flash 2 is specifically optimized for speed and low latency, offering significantly faster response times compared to many standard language models while maintaining good quality.

Does Ray Flash 2 support streaming responses?

Yes, Ray Flash 2 supports streaming responses, making it suitable for real-time applications where immediate feedback is important.

What is the performance-quality tradeoff with Ray Flash 2?

Ray Flash 2 provides an excellent balance of speed and quality, offering very fast responses while maintaining competent performance on general language tasks at an unbeatable price point.

Is Ray Flash 2 suitable for high-volume applications?

Absolutely, Ray Flash 2's combination of speed, low cost, and reliability makes it perfect for high-volume applications, batch processing, and scalable AI solutions.

Ray Flash 2

API Try this model

Luma Ray-Flash-2 is a faster, more cost-effective model for video generation.

Modalities: Text, Image, Video
Video
Price: $0.0274per 1M pixels
Model ID: luma/ray-flash-2
Released: Dec 2, 2025

Overview

Ray Flash 2 by Luma AI

Its optimized architecture supports fast iteration, preview, and production workflows for professional video, VFX, and multimedia applications.

Generated with Ray Flash 2 through AI/ML API on Nov 3, 2026. Prompt: A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion

Ray Flash 2 API Overview

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.

Technical Specifications

Output Resolution: Supports up to 720p with high detail preservation.
Supported Lengths: Generates videos of 5 or 9 seconds duration, suitable for short clips and social media content.
Input Mode: Text prompts combined with optional start frames or sketches for guided generation.
Processing Speed: Significantly optimized for rapid iterations, enabling faster preview cycles and production workflows.
Architecture: Built on a scaled-up multi-modal architecture, with a focus on motion coherence and visual quality.

Key Features

Fast Iterations & Previews: Designed for accelerated workflows, allowing users to generate previews swiftly during the creative process.
Realistic, Coherent Motion: Maintains logical and natural motion sequences with physics-based simulations and camera techniques.
High Fidelity Detailing: Produces photorealistic and visually rich videos with accurate lighting, shadows, and textures.
Multi-Modal Input: Supports text prompts, start frames, and sketches for flexible content control.
Scene Complexity Handling: Capable of rendering complex scenes with multiple interacting objects, dynamic environments, and atmospheric effects.

Code Sample

Comparison with Other Models

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.

‍

Pricing

Ray Flash 2 pricing in US dollars
Usage	Price	Unit
Usage	$0.0274	per 1M pixels

Quick start

View docs

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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 slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "luma/ray-flash-2",
    "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}

response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "luma/ray-flash-2",
    "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

The request returns a generation id. Poll GET https://api.aimlapi.com/v2/video/generations?generation_id=<id> until the status is completed.

Frequently asked questions

What inputs and outputs does Ray Flash 2 support?

Ray Flash 2 takes image, text as input and returns video.

When was Ray Flash 2 released?

Ray Flash 2 became available on December 2, 2025.

How is Ray Flash 2 billed?

Ray Flash 2 is billed per generation, a fixed charge per output rather than by prompt length.

Can Ray Flash 2 take an existing image as input?

Yes, Ray Flash 2 accepts image input as well as a text prompt.

Who created Ray Flash 2?

Ray Flash 2 was built by Luma AI.

How do I call Ray Flash 2 on AI/ML API?

Send a request to v2/video/generations with luma/ray-flash-2 as the model id.

Is Ray Flash 2 available through a single API key?

Yes. Ray Flash 2 is served through AI/ML API, so the same key and endpoint format used for other models applies.

What is Luma Ray Flash 2?

Ray Flash 2 is a video generation model from Luma AI, designed to be faster and more cost-effective than other Luma models.

Start building with Ray Flash 2

Get API key

Ray Flash 2 API

luma/ray-flash-2

Build with your agent

Give your agent the model details, code and documentation.

1Get your API key

Create API key

export AIMLAPI_KEY="8f2b4c7d9a1e6b3f…"

2Make your first request

curl '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 slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}'

import os
import requests

headers = {
    "Authorization": f"Bearer {os.environ['AIMLAPI_KEY']}",
    "Content-Type": "application/json",
}
payload = {
    "model": "luma/ray-flash-2",
    "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
}

response = requests.post("https://api.aimlapi.com/v2/video/generations", headers=headers, json=payload, timeout=120)
response.raise_for_status()
print(response.json())

const response = await fetch("https://api.aimlapi.com/v2/video/generations", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.AIMLAPI_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    "model": "luma/ray-flash-2",
    "prompt": "A slow dolly shot through a sunlit greenhouse full of ferns, light dust in the air, natural camera motion"
  }),
});

if (!response.ok) throw new Error(`HTTP ${response.status}`);
console.log(await response.json());

Docs for AI agents Plain-text index · llms.txt API documentation API reference and examples

Ray Flash 2

Overview

Ray Flash 2 by Luma AI

Ray Flash 2 API Overview

Technical Specifications

Key Features

Code Sample

Comparison with Other Models

Pricing

Quick start

Build with your agent

1Get your API key

2Make your first request

Related models

Ray 3.2

Ray 2

Luma Dream Machine Ray-2

Luma AI API

Frequently asked questions

Start building with Ray Flash 2