Runway Gen-4.5 is Runway's flagship AI video model for creators who need cinematic, prompt-accurate clips without a film crew. It turns a single sentence or a reference image into 2-to-10-second shots at 720p, with tightly controlled camera moves and consistent characters across frames. It sits at the top of public video Elo leaderboards, ahead of Runway's older Gen-3 and Gen-4 generations.
Core Features
- Text-to-video and image-to-video: describe a scene or upload a still, and Gen-4.5 animates it while preserving the subject's look.
- Complex prompt adherence: sequence multiple actions, camera choreography, and timing cues inside one prompt.
- Multiple aspect ratios (16:9, 9:16, 1:1, 4:3, 21:9) at 24 or 25 fps, plus ProRes or PNG-sequence export on higher tiers.
- One platform, many engines: Runway also ships Aleph 2.0 editing and routes to partner models like Google's Veo 3.1 and ByteDance's Seedance 2.5.
- Developer API: a single SDK call generates video, with cost routed per model through Model Router.
Use Cases
- Short-form creators making ads or social clips who need believable motion fast.
- Studios prototyping storyboards and previsualization before a live shoot.
- Marketers localizing product videos with consistent branding and characters.
Pricing
Runway uses a credit system. The Free plan gives 125 one-time credits. Standard starts at $12 per month (about 52 seconds of Gen-4.5 video), Pro at $28 per month, and Max at $76 per month with rollover. Via API, Gen-4.5 costs roughly $0.12 per second. It stays cheaper per second than many rivals, though credits disappear quickly on long renders.
Our Take
Best for professionals who care about realism and camera control over raw volume. Trade-off: the credit meter burns fast, so budget by the second, not the clip. Explore more AI Video tools.
