Shotcraft
Video generation

Runway Gen-4.5

Runway's current flagship generation model, producing video from text alone or from a starting image.

A video generation model by Runway · read 2026-08-14 · sourcing medium

Up to
10 seconds
Resolution
1080p
Aspect ratios
16:9, 9:16
Weights
Not released
API
Yes
Commercial use
Permitted subject to conditions

Announced 2025-12-01 for the web app and added to the developer API on 2026-02-10. Runway reports it took the top position on the Artificial Analysis text-to-video leaderboard at launch with 1,247 Elo.

Commercial use — Permitted subject to conditions

Commercial use enabled on paid plans; watermarks removed from the Standard tier upward.

  • Depends on your plan tier. Commercial use enabled on paid plans; watermarks removed from the Standard tier upward
  • Output is watermarked. Commercial use enabled on paid plans; watermarks removed from the Standard tier upward

The conditions above were extracted from the licence notes recorded during research, and each one shows the sentence it came from so you can check the reading. Read the licence before you rely on any of this. Nothing on this page is legal advice, and this site does not tell you a model is cleared for commercial use.

Specification

Vendor figures, read 2026-08-14Read from Runway's own documentation on 2026-08-14. Vendors change these between model versions without announcing it, so check theirs before you commit a shot to a number. Sourcing for this entry is mixed. Some fields came from pages we retrieved, others could not be confirmed and are left blank. Check the vendor's current documentation

What it takes in
text, image
What it makes
video
Maximum duration
10 seconds
Maximum resolution
1080p
Aspect ratios
16:9, 9:16
Controls
image-to-video, keyframes
Weights
Not released
API
Yes
Pricing
credit-based; API 12 credits per second of output at $0.01 per credit ($0.12/sec). Web app included in all paid subscription tiers
Released or updated
2025-12-01

Strengths

  • Strong prompt adherence and motion quality per Runway's own benchmark claims
  • True text-to-video, not image-only like Gen-4 Turbo
  • Flexible integer duration from 2 to 10 seconds via the API
  • Cheaper per second than Veo 3.1 or Sora 2 Pro

Weaknesses

  • No native audio generation
  • 10-second ceiling
  • Runway itself documents causal reasoning errors, object permanence failures and success bias in action outcomes
  • API ratio options documented as only 1280:720 and 720:1280

Best for

Where the sources disagree

Recorded rather than resolved. Picking the tidier number would hide the fact that the vendor's own pages do not agree.

What to understand before using it

Explainers naming the mechanisms this model's own documentation mentions.

MCP servers that front Runway

Servers in the media MCP directory whose own description or homepage names this vendor. Absence of a server here is not evidence that none exists: most publish no tool list at all.

9 further servers name Runway with lower confidence and are not listed, because a server naming a vendor may be using it for text rather than media.

See it from the vendor

Shotcraft hosts no sample output. Judging a model means watching its own showreel with your own eyes, and a clip re-hosted here would be a clip we chose.

Nearby in the directory

Runway Act-Two

Performance transfer model. You supply a character as an image or video plus a driving reference video of a person performing, and Act-Two maps that p

Video generation

Runway Aleph 2.0

In-context video editing model. It takes an existing video plus a text instruction and optional keyframe images, and re-renders the footage to add, re

Video generation

Runway Gen-4 Aleph

First-generation Aleph video-to-video editing model, which introduced prompt-driven in-context editing of existing footage at Runway. Discontinued on

Video generation

Sources

Read on 2026-08-14. A source that has changed since then will not be reflected here until the next pass.