DigestAI news desk

Cut through the AI noise.

Enterprise & Industry3 min read

Baseten adds Runway’s Gen-4.5 and Aleph 2.0 to dedicated inference

Baseten announced on October 14, 2026, that enterprises can now deploy Runway’s Gen-4.5 and Aleph 2.0 video models in secure, single-tenant environments via Baseten Dedicated Inference. The models—licensed directly from Runway—expand beyond Runway’s existing platforms (Creative and Dev) to allow on-premise or cloud-based deployment with full isolation and compliance controls.

1 source

Key points

  • Baseten Dedicated Inference now supports Runway’s Gen-4.5 and Aleph 2.0 models in isolated, single-tenant environments
  • Models licensed directly from Runway with proprietary terms, deployable on Baseten Cloud, self-hosted, or hybrid setups
  • Customers gain fine-tuning, reserved GPU capacity, and 99.99% uptime SLA for video generation and editing workloads

Gen-4.5 generates cinematic video from text or images, supporting detailed scene direction and multiple visual styles. Aleph 2.0 edits existing footage, enabling changes to elements like products, backgrounds, or styles across multi-scene videos up to 30 seconds at 1080p. Customers can fine-tune models on their own data and reserve GPU capacity for consistent performance. Baseten highlights compliance (SOC 2 Type II, HIPAA, GDPR) and lists clients like Amazon, Robinhood, and Microsoft already using Runway in production.

Full story from Unite.AI · by Theo Nash, AI Infrastructure & Compute, AI Research AgentOpen source ↗

Baseten Adds Runway’s Gen-4.5 and Aleph 2.0 to Dedicated Inference

Unite.AI · 14 October 2026

Loading the full article…

This text was published by Unite.AI and written by Theo Nash, AI Infrastructure & Compute, AI Research Agent. It is reproduced here with attribution so you can read it in full; the rights remain with the publisher. Read it at the source ↗

Topics · follow one to build your own front page

The headline, key points and digest above were generated by Digest AI's editorial model from the linked sources. Automated summaries can contain errors: the sources are the record. Spotted a mistake? Tell us. Published by Martin K., who runs Digest AI and handles corrections.

Comments

via GitHub Discussions

More in Enterprise & Industry

All →

Related stories