Filmmakers and ad makers wanting strong prompt adherence in short clips; the cheapest plan buys under a minute of Gen-4.5 footage a month.
Kenning's take
What it does
Gen-4.5 is Runway's video model, announced on 1 December 2025, aimed at better motion, prompt adherence and visual detail than Gen-4 while keeping its speed. Runway says it ranked first on the Artificial Analysis text-to-video leaderboard at launch. It is available on Runway's paid subscription plans and through the Runway API.
- Text-to-video and image-to-video generation
- Physics-aware motion for objects and liquids
- Precise prompt adherence for complex scenes
- Same speed as Gen-4
- Control modes such as keyframes and video-to-video planned
Who it suits. Filmmakers, advertisers and creators who generate short video clips from prompts.
Key facts
- Category
- AI models
- Part of
- Runway
- Made by
- Runway
- Based in
- United States
- Released
- 1 December 2025
- How to get it
- in the Runway web and mobile apps on Standard, Pro and Max plans, and through the Runway API
- Works on
- Web, iOS, Android, API
- Free plan
- 125 one-time credits on the free plan
- API price
- Gen-4.5 costs 60 credits per 5 seconds on subscription plans; API price not checked
Pricing
| Plan | Price | Billed |
|---|---|---|
| Standard | $12 | month, billed annually ($15 monthly) |
| Pro | $28 | month, billed annually ($35 monthly) |
| Max | $76 | month, billed annually ($95 monthly) |
FAQ
When was Runway Gen-4.5 released?
Runway announced Gen-4.5 on 1 December 2025.
Is Runway Gen-4.5 free?
The free plan gives 125 one-time credits; regular use needs a paid plan from $12 a month billed annually.
How much video does a Standard plan make?
625 monthly credits, which Runway says is about 52 seconds of Gen-4.5 video.
Facts from the maker's own pages and the sources listed. Checked 2026-10-11.
Similar tools
Runway Aleph
Runway's video model that edits existing footage from text, adding or removing objects and changing angles or light
ACE-Step 1.5
Open-source music generation model that writes full songs with lyrics and runs on ordinary consumer GPUs.
AlphaGenome Atlas
Google DeepMind database of AI-predicted effects for every possible single-letter change in human DNA.
Amazon Nova 2
Amazon's second family of Nova AI models, covering reasoning, speech conversation and combined text-and-image generation.