Runway Gen-4.5 is an AI video generation model by Runway, released December 1, 2025, that generates cinematic, physically accurate video from text prompts — ranked #1 on the Artificial Analysis Text-to-Video benchmark at 1,247 Elo, ahead of every rival model at launch.
Built for filmmakers, marketers, and creative teams, it turns briefs into precise, sequenced motion with cause-and-effect accuracy — handling complex multi-step actions and event scripting that earlier models rendered with visible jitter.
Sequenced action, complex motion, physically accurate scenes, social-native video, VFX sequences
Film and marketing teams that need precise, sequenced motion and cause-and-effect accuracy
The benchmark-leading model for physically accurate, sequenced motion.
Objects move with realistic weight, momentum, and force. The advancement extends to fluid dynamics, surface rendering, and fine details like hair and fabric textures, which maintain coherence across motion and time — this is the core claim behind Runway's #1 benchmark position.
Characters and objects move naturally through multi-step actions without the jitter or discontinuity common in earlier AI video. Runway calls out its handling of sequenced physical actions as a specific, tested improvement over Gen-4.
Describe a sequence of events in plain language and Gen-4.5 renders them in the correct causal order — a meaningful step up in prompt adherence for scenes that involve more than one action.
Gen-4.5 maintains the speed and efficiency of Gen-4 despite the quality jump — Runway explicitly designed it to deliver breakthrough quality without slowing down generation or raising cost for existing plans.
The widest aspect ratio selection in the Runway lineup, including 21:9 cinematic widescreen, alongside 16:9, 9:16, 4:3, 3:4, and 1:1 — giving film-style projects a native format rather than a crop.
Runway 4.5 fits wherever teams need physically accurate, sequenced video for short-form and social placements.
Add a node, script the sequence, and generate physically accurate motion.
Add a Runway 4.5 node to the canvas and describe your scene in a text prompt, optionally providing a first-frame image to guide the generation. Choose your aspect ratio, including 21:9 for cinematic widescreen.
Choose a 5 or 10 second duration. Describe camera choreography, scene composition, event timing, and atmospheric changes within a single prompt — the model handles detailed, sequenced instructions well.
Chain the node with an image model for the first frame, an upscaler for delivery resolution, or an audio node for sound, then export with commercial rights on your plan.
Real generated videos with the exact prompts — copy any prompt and run it yourself.
One subscription across 30+ AI models — no per-tool credit balances or separate signups. Credit cost per generation is shown live in the node before you run it.
500 weekly credits to test the model and see the output quality. No credit card required.
45,000 monthly credits with cheaper per-credit pricing, commercial rights, and video download.
90,000 monthly credits, up to 10 seats, shared workspace, centralized billing, and priority support.
210,000 monthly credits, API and integration support, unlimited seats, and dedicated management.
Full specs for Runway Gen-4.5.
How Runway 4.5 compares with other AI video models in the Phygital+ catalog.
Chain image, video, upscaling, and audio into one repeatable workflow.
Design the first frame with an image model, then animate it with Runway 4.5 in one workflow.
Generate with Runway 4.5, then upscale to delivery resolution for film, ads, or broadcast.
Add narration or sound design with a dedicated voice or audio node.
Write the script and shot list with a text model, then feed it straight into video generation.
Everything you need to know about Runway 4.5 in Phygital+.
Runway Gen-4.5 is Runway's flagship AI video generation model, released December 1, 2025. It generates cinematic, physically accurate video from text prompts or a first-frame image, and held the #1 spot on the independent Artificial Analysis Text-to-Video benchmark at launch with 1,247 Elo points.
Usage is credit-based and included in every Phygital+ plan — from the free plan up to Enterprise. The exact credit cost per generation is shown live in the node before you run it, so you can start for free and scale as you go. This is separate from Runway's own subscription pricing for Gen-4.5.
Outputs created on any paid plan (Starter and up) come with commercial-use rights. Check the model card for any provider-specific limits, particularly around depicting real, identifiable people.
Runway 4.5 is made by Runway, a company founded in 2018 that released Gen-1 — the first publicly available video generation model — in 2023. Runway is valued at roughly $3.55 billion (PitchBook estimate) and counts media organizations, studios, brands, and creatives among its customers.
Gen-4.5 was internally codenamed "David," a reference to the David and Goliath story — CEO Cristóbal Valenzuela described the roughly 100-person team outcompeting trillion-dollar AI labs on an independent, blind-voted benchmark as the inspiration for the name.
Clips run at a fixed 5 or 10 second duration. This predictable pacing is designed for easy integration into longer edits rather than variable-length generation.
Native audio generation and native audio editing were added in May 2026 via an ElevenLabs integration, several months after the initial December 2025 launch, which shipped as a silent video model.
Gen-4 Turbo is the prior-generation model that added native 4K output (Gen-3 topped out at 720p native with 4K upscale). Gen-4.5 is the newer flagship focused on motion quality and physical accuracy; check current documentation for which model ships native 4K by default.
Yes. Runway offers the model through its own platform, API, and select partners. In Phygital+, you can run Runway 4.5 as a node on any plan, and API and integration support is available on the Enterprise plan.
Running Runway 4.5 in Phygital+ means no separate Runway account or credit balance for one model: it sits on the same canvas as 30+ other AI tools. Chain image generation, video, upscaling, and audio into one repeatable workflow under a single subscription.
Browse the full catalog of 30+ AI models available in Phygital+.
Join 100+ teams using Phygital+ – every model in one workspace
Try Phygital+ free
