RailwailRailwail

Runway Gen 4.5

New
Popular
Replicate
Video Generation

Top-ranked for motion quality and visual fidelity

Queue video with Runway Gen 4.5
Video generation runs asynchronously — we'll queue a job and you can track it in your history.
Sign in to try this model with €5 free credits.
Sign in
Generates as an async job — typically 30 s to 2 min.
TL;DR·Last updated March 25, 2026

Runway Gen 4.5 is video generation AI model from Replicate, priced at €0.000 per 1M input tokens with a unknown context window.

Try Runway Gen 4.5
Sign in to generate — 50 free credits on sign-up

Examples

See what Runway Gen 4.5 can generate

0:10

Cinematic

"Woman walking through sunflower field, golden hour"

Pricing

Price per Generation
Per generation€1.00

API Integration

Use our OpenAI-compatible API to integrate Runway Gen 4.5 into your application.

Install
npm install railwail
JavaScript / TypeScript
import railwail from "railwail";

const rw = railwail("YOUR_API_KEY");

// Simple — just pass a string
const reply = await rw.run("runway-gen45", "Hello! What can you do?");
console.log(reply);

// With message history
const reply2 = await rw.run("runway-gen45", [
  { role: "system", content: "You are a helpful assistant." },
  { role: "user", content: "Explain quantum computing simply." },
]);
console.log(reply2);

// Full response with usage info
const res = await rw.chat("runway-gen45", [
  { role: "user", content: "Hello!" },
], { temperature: 0.7, max_tokens: 500 });
console.log(res.choices[0].message.content);
console.log(res.usage);
Specifications
Price
€1.00
Avg. latency
30.0s
Est. duration
30s
Developer
Replicate
Category
Video Generation
Supported Formats
mp4
Tags
popular
top-quality

Deep dive — Runway's Runway Gen 4.5

About Runway
Founded 2018 · New York City, USA

Runway was founded in 2018 in New York City by Cristobal Valenzuela, Anastasis Germanidis and Alejandro Matamala-Ortiz, three NYU ITP graduates who set out to build AI-native creative tools. Runway co-authored the Stable Diffusion paper (Rombach et al., 2022) with CompVis and LMU Munich and has shipped Gen-1 (2023), Gen-2 (2023), Gen-3 Alpha (June 2024), Gen-3 Alpha Turbo (July 2024), Gen-4 (March 2025) and Gen 4.5 (mid-2025). Gen 4.5 is the incremental update to Gen-4 with higher fidelity, longer durations and improved character consistency. The company has raised over $300M from Google, NVIDIA, Salesforce Ventures and General Catalyst at a $3B+ valuation, and runs the annual AI Film Festival as well as Hollywood-studio partnerships.

Visit Runway →
Architecture
Latent video diffusion model (Diffusion Transformer) with reference and motion adapters

Runway Gen 4.5 is a closed Diffusion Transformer operating on a learned spatio-temporal latent space, building on the Gen-4 foundation released in early 2025. The model is conditioned on a multilingual text encoder plus optional image, reference-frame and motion-reference inputs. Gen-4 introduced character-, object- and environment-reference modes that let users lock identity, props or backgrounds across multiple shots; Gen 4.5 expands the reference vocabulary and improves consistency for longer sequences. Native generation is up to 10 seconds per clip at 720p (with 1080p upscale), and Runway's editor chains generations into multi-shot scenes. Gen 4.5 also tightens the integration with Runway's Act-One performance capture, Motion Brush, Lip Sync and Camera Control features. Training uses internal video, licensed footage and partner data on Runway's multimodal training infrastructure.

Parameters
Undisclosed
Context
unknown
What it can do
  • Text-to-video and image-to-video at up to 720p (1080p via upscale)
  • 10-second clips per generation, chainable into multi-shot scenes
  • Character-, object- and environment-reference modes for cross-shot consistency
  • Tight integration with Act-One performance capture, Motion Brush and Lip Sync
  • Strong cinematic camera-language and Camera Control sliders
  • Available via Runway web app, mobile app and API
  • Used in production by Hollywood studios for previs and inserts
  • Public model card and ongoing safety programme
  • Best for: film previs, ad creative, multi-shot narratives, character-driven content.
Training & License

Curated mix of internal video, licensed footage and partner data on Runway's multimodal training infrastructure; exact corpus size undisclosed.

License: Proprietary commercial licence via Runway Terms of Service; generated content usable commercially on paid plans.

Known limitations
  • 10-second clip limit per generation
  • 1080p only via upscale
  • No native audio
  • Closed model with no full technical paper
  • Reference modes can drift on long sequences

Research papers

Frequently asked questions

Related Models

View all Video Generation

Google Veo 2

Google DeepMind

Google's state-of-the-art video generation model. Simulates real-world physics with various visual styles.

€5.00

Google Veo 3

Google DeepMind

Google's Veo 3. High-fidelity text-to-video with native audio generation, up to 8s clips.

€0.75

Google Veo 3.1

Google DeepMind

Latest Veo with image-to-video and context-aware audio

€6.00

Kling v3

Replicate

Cinematic video up to 15s with multi-shot and native audio

€2.00

Start using Runway Gen 4.5 today

Get started with free credits. No credit card required. Access Runway Gen 4.5 and 100+ other models through a single API.

Get Started FreeBrowse All Models