- - 🆕 Runway's latest flagship video generation model, released April 2026.
- - 🎯 Generates high-definition video from text prompts and reference images.
- - 👁️ Runway highlights detailed compositions, physical accuracy, and expressive characters.
- - 🎬 Emphasizes visual fidelity and precise creative control.
- - 🔧 Available through Runway's API using the gen4.5 model identifier.
- - 📚 Builds on Gen-4's character, location, and object consistency.
- - 🏢 Made by Runway, a New York generative-AI video company.
- - ⚡ Offered alongside Gen-4 Turbo and the Aleph video-to-video model.
Runway AI, Inc. is an American generative AI company based in New York City, focused on research and commercial products for synthesizing video, images, and other multimedia. The lab is best known for its text-to-video and video-to-video generative models, which have helped…
Explore 1 more model by Runway (company) →Runway Gen-4.5 is the newest flagship in Runway's video lineup, introduced in April 2026 as a model that turns text prompts and reference images into high-definition footage. Runway describes it as offering strong visual fidelity and creative control, and says the model excels at detailed compositions, physical accuracy, and expressive characters. It is available through Runway's developer API, where the gen4.5 identifier handles image-to-video tasks driven by a text prompt.
Compared with its predecessor Runway Gen-4 Turbo and the broader Gen-4 generation, Gen-4.5 extends Runway's earlier focus. The original Gen-4 was built primarily around world consistency, letting creators maintain coherent characters, locations, and objects across scenes from reference imagery. Gen-4.5 broadens this toward stronger text-driven generation while retaining that consistency foundation, according to Runway's research notes.
A companion text-to-video configuration, Runway Gen-4.5, shares the same April 2026 release date and emphasizes prompt-based creation more than the image-led approach of Gen-4. It sits alongside Runway Gen-4 Aleph, a separate video-to-video model intended to edit existing clips or generate subsequent shots in a sequence.
Together these models form Runway's current toolkit for cinematic content creation, spanning text-to-video, image-to-video, and video-to-video workflows.
This About section is AI-generated from public sources via VeniceStats + Venice inference, with no human editing. It may contain inaccuracies.
Daily usage · Runway Gen-4.5 · Organic sellers
| Seller | Health | Rep↓ | Sales | Video | Routing | $ / s | $ / video |
|---|---|---|---|---|---|---|---|
| ▲ Apex Ant 0x73b4…e736 | — | 81.71 | — | — | #2 | $0.0729 | — |
| Venice.ai Proxy 0x1f22…18c9 | failingupstream error · 3.7 h | 86.84 | $5.14 | 1 min | #1 | $0.0891 | — |
"Best price" and the seller table are live Antseed catalog data (advertised $/1M tokens — or $ per generated image for unit-billed image models — not settled amounts). Reputation = buyer trust score (0-100, the Antseed SDK's own formula). "Routing" = the SDK's default buyer routing (what the VPR desktop app ships with): a trust ≥ 60 gate on the effective reputation, then cheapest-first among routable sellers; live failover state (per-peer cooldowns) is buyer-side runtime and not included. Model knowledge (TLDR, provider, About) via the VeniceStats enrichment layer. Advertised catalog, not the model used in any specific purchase. "Usage on Antseed" counts only settlements whose buyers share the per-model split on-chain (metadata v2/v3, opt-in), so every usage figure is a lower bound.