Pricing Blog
Runway · Runway's frontier video foundation model.

Runway Gen-4.5

The Model That Debuted at #1

Runway Gen-4.5 is the studio's frontier foundation model, delivering photorealistic, physics-aware video with the prompt precision that took it to the top of the Artificial Analysis leaderboard.

1,247
Elo (Artificial Analysis)
#1
Text-to-Video rank at launch (Dec 2025)
Up to 10s
Clip length
720p
HD output
What's new

The Model That Debuted at #1

01

Benchmark leader at launch

Scored 1,247 Elo on the Artificial Analysis Text-to-Video leaderboard at launch, edging out Google Veo 3, Kling 2.5 and OpenAI Sora 2 Pro.

02

Believable physics

A stronger world model gives motion real weight and momentum, with cause-and-effect and human movement that hold up shot to shot.

03

Cinematic control

Six aspect ratios from vertical 9:16 to ultrawide 21:9, plus Image-to-Video control, with more modes such as Keyframes and Video-to-Video announced by Runway.

04

Gen-4 speed retained

Built on NVIDIA Hopper and Blackwell GPUs, it keeps the responsiveness of Gen-4 while stepping up fidelity.

Overview

Model at a glance

Runway Gen-4.5 is Runway's frontier video generation model, released on December 1, 2025 as the successor to the Gen-4 family. Runway positions it as a general-purpose foundation model for world modeling, built on gains in pre-training data efficiency and post-training technique rather than raw scale alone. At launch it took the top spot on the Artificial Analysis Text-to-Video leaderboard with 1,247 Elo, ahead of Google Veo 3, Kling 2.5 and OpenAI Sora 2 Pro.

The model's headline strength is a stronger internal world model: motion carries realistic weight and momentum, characters move and emote convincingly, and complex scenes stay coherent while closely following the prompt. Gen-4.5 debuted as text-to-video; Runway added Image-to-Video in January 2026 and has said more control modes, such as Keyframes and Video-to-Video, are on the way. As of August 2026 it remains Runway's frontier model, with no Gen-5 announced.

Developer
Runway
Model family
Gen-4.5
Released
December 1, 2025
Modality
Text-to-video & image-to-video
Launch benchmark
1,247 Elo, #1 Text-to-Video (Artificial Analysis)
Aspect ratios
16:9, 9:16, 1:1, 4:3, 3:4, 21:9
Clip length
2–10 s (5 s or 10 s on SharkFoto)
Max resolution
720p HD
Capabilities

Key features

Leaderboard-topping quality

Gen-4.5 scored 1,247 Elo on the Artificial Analysis Text-to-Video leaderboard at launch, placing first ahead of Google Veo 3 (1,226), Kling 2.5 (1,225) and OpenAI Sora 2 Pro (1,206) in blind human preference testing.

Physics-aware world model

Improved world modeling gives objects and characters believable weight, momentum and interaction, so motion and cause-and-effect look natural rather than drifting or sliding.

Precise prompt adherence

The model closely interprets detailed prompts — subject, action, camera and style — producing complex, well-composed scenes that match what you described.

Expressive characters

Generates photorealistic and stylized characters with lifelike facial detail and expression, holding a consistent look across a shot.

Cinematic aspect ratios

Supports 16:9, 9:16, 1:1, 4:3, 3:4 and ultrawide 21:9, covering social verticals, square posts and widescreen cinematic framing from one model.

Expanding control modes

Beyond text-to-video, Gen-4.5 supports Image-to-Video (added January 2026), letting you drive a shot from a real, generated or illustrated still; Runway says more control modes such as Keyframes and Video-to-Video are on the way.

Efficient by design

Running on NVIDIA Hopper and Blackwell GPUs, Gen-4.5 preserves the speed and efficiency of Gen-4 while raising output fidelity.

Specs

Technical specifications

Generation

Primary modalityText-to-video
Control modesImage-to-Video (Keyframes and Video-to-Video announced, not yet available)
Clip durations2–10 s (5 s or 10 s on SharkFoto)
Max resolution720p (4K only via Runway's separate Upscale tool)

Formats

Aspect ratios16:9, 9:16, 1:1, 4:3, 3:4, 21:9
OrientationLandscape, portrait, square, ultrawide

Performance

Launch benchmark1,247 Elo, #1 on Artificial Analysis Text-to-Video
ComputeNVIDIA Hopper & Blackwell GPUs
AccessRunway platform, API and select partners
In practice

Use cases

Cinematic shots & trailers

Generate establishing shots, dynamic sequences and moody cinematic moments in 21:9 or 16:9 with realistic motion and lighting.

Social video

Produce vertical 9:16 and square 1:1 clips for Reels, TikTok, Shorts and Stories directly in the right frame.

Product & advertising

Create polished product shots and ad concepts with photorealistic detail and precise prompt control for fast creative iteration.

Character-driven storytelling

Animate expressive, consistent characters — photorealistic or stylized — for narrative pieces, explainers and concept films.

Image-to-video animation

Bring a real, generated, sketched or illustrated still to life by driving motion from a first-frame image.

Generational leap

Runway Gen-4.5 vs Runway Gen-4

Gen-4.5 keeps Gen-4's speed and six aspect ratios while improving physics, prompt adherence and overall quality, which took it to #1 on the Artificial Analysis leaderboard at launch.

FeatureRunway Gen-4Runway Gen-4.5NEW
Artificial Analysis rankBelow frontier leaders#1 Text-to-Video at launch, 1,247 Elo
World model / physicsStrong consistencyImproved weight, momentum and cause-and-effect
Prompt adherenceGoodHigher fidelity to complex prompts
Aspect ratiosSix ratios incl. 21:9Same six ratios (16:9, 9:16, 4:3, 3:4, 1:1, 21:9)
SpeedFast, efficientRetains Gen-4 speed at higher quality
Honest look

Current limitations

Causal reasoning gaps

The model can still misorder cause and effect, so an effect occasionally appears before the action that should produce it.

Object permanence

Objects may occasionally disappear, reappear or shift unexpectedly across frames in complex or fast-moving scenes.

Success bias

Generated actions tend to resolve favorably by default, which can make outcomes look unrealistically successful without careful prompting.

Short clip lengths

Individual generations are capped at short durations (up to 10 seconds; 5 s or 10 s on SharkFoto), so longer sequences require stitching multiple clips together.

FAQ

Frequently asked questions

What is Runway Gen-4.5?
Gen-4.5 is Runway's frontier video generation model, released December 1, 2025. It generates video from text prompts or from a first-frame image (Image-to-Video) and serves as Runway's foundation model for world modeling.
How good is Gen-4.5 compared to other video models?
At launch it ranked #1 on the Artificial Analysis Text-to-Video leaderboard with 1,247 Elo, ahead of Google Veo 3 (1,226), Kling 2.5 (1,225) and OpenAI Sora 2 Pro (1,206) in blind human preference testing.
What aspect ratios and lengths does Gen-4.5 support?
It supports 16:9, 9:16, 1:1, 4:3, 3:4 and ultrawide 21:9 aspect ratios, with clips of 2 to 10 seconds (5 or 10 seconds on SharkFoto) at 720p.
Can Gen-4.5 animate my own images?
Yes. Gen-4.5 launched as text-to-video and Runway added Image-to-Video afterward (live in January 2026), letting you drive a video from a first-frame still. Keyframes and Video-to-Video modes have been announced but are not available yet. On SharkFoto, upload one image in the Image to Video tool.
Is there a Runway Gen-5 yet?
No. As of August 2026 Runway has not announced a Gen-5, and Gen-4.5 remains the studio's frontier video model.
What are Gen-4.5's main weaknesses?
Runway notes it can still struggle with causal reasoning, object permanence and a bias toward successful outcomes, and clips are limited to short durations of up to 10 seconds.
Can I use Runway Gen-4.5 on SharkFoto?
Yes. Runway Gen-4.5 is available on SharkFoto in Text to Video and Image to Video, with 5- or 10-second clips in 16:9, 9:16, 4:3, 3:4, 1:1 and 21:9; Image to Video takes one input image.

Create with Runway Gen-4.5 on SharkFoto

Turn a prompt or a single image into a cinematic, physics-aware 5- or 10-second clip in any of six aspect ratios, right on SharkFoto.

Try Runway Gen-4.5 now