This is RCTV’s living reference to the AI video generation landscape. Updated regularly as models launch, pricing changes, and capabilities evolve. Last updated: April 4, 2026.

The Big Seven: Commercial Models

These are the production-grade models dominating professional and creator workflows in early 2026. The market has matured to the point where no single model leads across all dimensions — the professional standard is now multi-model routing, choosing the right tool for each specific shot.

Sora 2 — OpenAI (Discontinued March 24, 2026)

OpenAI shut down Sora on March 24, 2026 — the app, the API, and the Disney licensing deal that was announced with it in December 2025. The stated reason was compute reallocation toward “world simulation for robotics.” The numbers tell the fuller story: estimated $15M/day peak inference cost against $2.1M in total lifetime in-app revenue, and a 66% download decline from its November 2025 peak to February 2026. Sora is removed from active tracking. See Weekly Roundup — March 27, 2026 for the full breakdown.

Shutdown timeline: The Sora app and web interface go dark April 26, 2026. Users have until then to export any content created on the platform. The Sora API remains accessible through September 24, 2026, giving developers time to migrate integrations.

Luma Ray 3.14 — Luma AI

Best for: Professional production volume, 1080p native output, cost-efficient multi-shot workflows

Luma AI’s Ray 3.14 is the most significant release of the week — and the model that steps into the commercial tier vacated by Sora’s shutdown. Native 1080p output, generation speed 4× faster than the previous Ray 3 model, and per-second pricing 3× cheaper. Ray3 Modify, a companion tool for hybrid performance and acting workflows, gives brands and studios more control over scene continuity and character consistency across shots.

Luma is positioning Ray explicitly as professional infrastructure priced for production volume rather than a consumer app — a distinction that looks strategically deliberate given Sora’s failure. The company’s $900M Series C led by HUMAIN, new London office, and enterprise Luma Agents deployments at Publicis, Adidas, and Mazda all reinforce this direction.

• Max resolution: 1080p native
• Key features: Ray3 Modify (hybrid performance/acting control), Luma Agents platform (enterprise creative automation)
• Speed: 4× faster generation than previous Ray model
• Pricing: 3× cheaper per-second than previous Ray
• Access: Luma AI subscription; free tier available
• API: Available; enterprise deployments via Luma Agents

Kling 3.0 — Kuaishou

Best for: Feature density, broadcast-ready output, motion quality

The most capability-dense model available. Kling 3.0 is the first AI video model to meet broadcast delivery standards without upscaling, offering native 4K at 60fps. The storyboard feature generates up to six camera cuts in a single generation with visual consistency — a production-first capability no other model matches.

• Max resolution: 4K native
• Frame rate: Up to 60fps
• Audio: Native built-in audio
• Key feature: Multi-cut storyboard generation
• Access: Free tier available; paid plans from ~$8/mo
• API: Available via Kuaishou and third-party platforms

Veo 3.1 — Google DeepMind

Best for: Photorealism, 4K native output, integrated workflows, broadest free access

Google’s model pushes photorealistic rendering to the point where trained observers struggle to identify generated footage in blind tests. The engine behind Google Flow (merged creative workspace with Whisk, ImageFX, and multi-clip sequencing) and now Google Vids, which received a major update this week.

As of April 3, 2026, any Google account holder can generate Veo 3.1 clips for free via Google Vids — 10 generations per month, 8 seconds at 720p, from text prompts or uploaded images. Google AI Pro and Ultra subscribers unlock more: up to 1,000 Veo clips per month, Lyria 3 custom music generation (tracks up to 3 minutes), customizable AI avatars with scene placement and wardrobe control, and direct YouTube export. This is the first time a production-grade AI video model has been made freely accessible to Google’s full account base.

On the developer side, Google launched Veo 3.1 Lite on March 31 via the Gemini API and Google AI Studio — priced at $0.05/sec for 720p and $0.08/sec for 1080p, less than half the cost of the existing Veo 3.1 Fast tier at the same generation speed. Supports text-to-video and image-to-video in 4-, 6-, and 8-second lengths, landscape and portrait. A further price reduction on Veo 3.1 Fast is scheduled for April 7.

• Max resolution: 4K native (Flow/Vertex AI); 1080p via Veo 3.1 Lite; 720p via Google Vids free tier
• Audio: Native synchronized audio
• Key features: Flow unified workspace; Google Vids integration (avatars, Lyria 3 music, YouTube export); Veo 3.1 Lite developer tier
• Access: Free — 10 clips/month via Google Vids (any Google account); Google AI Pro ($19.99/mo) and Ultra for higher limits; Flow is free
• API: Vertex AI ($12/min); Veo 3.1 Lite via Gemini API ($0.05/sec 720p, $0.08/sec 1080p); Veo 3.1 Fast price cut April 7
• Milestone: 1.5 billion images and videos created by Flow users

Seedance 2.0 Pro — ByteDance

Best for: Character consistency, cinematic motion, multi-shot storytelling

The top-ranked model on Artificial Analysis for both text-to-video and image-to-video, ahead of Veo 3, Sora, and Kling. Seedance 2.0 Pro’s Dual-Branch Diffusion Transformer generates audio and video simultaneously in a single pass. Its quad-modal input system accepts text, images, video, and audio in a single prompt. Multi-shot native storytelling and frame-level control over character appearance, object placement, and scene timing set it apart for narrative work.

ByteDance’s official global API rollout was paused indefinitely in late February 2026 after the Motion Picture Association and major studios (Disney, Netflix, Paramount, Sony, Warner Bros.) issued cease-and-desist letters over copyright concerns. The “Face-to-Voice” feature was suspended on February 10 after it was shown to clone voices from a single photo. Japan opened a separate inquiry over unauthorized anime character reproductions.

On March 23, 2026, ByteDance moved anyway — relaunching the model as Dreamina Seedance 2.0 across markets in Africa, South America, the Middle East, and Southeast Asia. The US is specifically excluded. The rebranding distances the product from ByteDance’s direct brand identity in markets where Chinese-owned AI platform scrutiny is intensifying. This is not a full global rollout — it is a geographic workaround that generates commercial traction and training data while the US legal situation remains unresolved.

The copyright landscape around Seedance grew more complex this week. The White House published its National Policy Framework for AI (March 2026) stating that AI training on copyrighted works does not constitute infringement — the opposite of the Blackburn bill’s position. Separately, the bipartisan CLEAR Act (Schiff/Curtis) would require public disclosure of training data without resolving the fair use question either way. Three incompatible federal positions now coexist: Blackburn (training = not fair use), White House (training = fine, let courts decide), CLEAR Act (disclose and defer).

• Max resolution: 2K
• Audio: Native audio with lip-sync
• Key feature: Multi-shot storytelling, quad-modal input, frame-level precision
• Access: China via Jimeng/Dreamina; global south (Africa, South America, Middle East, SE Asia) via Dreamina Seedance 2.0 (March 23); global via BigMotion ($35–$95/mo), LumeFlow AI, other third-party platforms; US excluded
• API: Official global API paused; available via third-party integrations
• Note: US access still frozen; ByteDance routing around via Dreamina rebrand in emerging markets; copyright legislative battle now a three-way standoff (Blackburn vs. White House vs. CLEAR Act)

Grok Imagine — xAI

Best for: Speed, low-cost API, rapid iteration, social media distribution

The newest entrant to the AI video generation field, and the fastest-iterating. xAI shipped four major updates in five weeks: API launch (January 28), Grok Imagine 1.0 with 720p video and audio (February 3), Grok 4.20 (February 17), and video extension (March 2). The “Extend from Frame” feature lets users chain clips by continuing from the final frame, enabling sequences up to 30 seconds while preserving lighting, motion, and character positioning.

Grok Imagine’s API pricing dramatically undercuts the field. The trade-off is a 720p resolution ceiling — every other major model offers 1080p or higher. Community testing also confirms visible quality degradation after two or three chained extensions.

The distribution advantage is unique: over 500 million X users have direct access. Video features are currently locked behind X Premium subscriptions.

• Max resolution: 720p
• Max duration: 30 seconds (via chained extensions)
• Audio: Synchronized audio
• Key feature: Video extension from frame, fastest iteration cycle in the industry
• Access: X Premium subscription required
• API: Available ($4.20/min generated video — cheapest major model)
• Engine: Aurora autoregressive model on 110,000 NVIDIA GB200 GPUs
• Caution: Faced regulatory scrutiny over content moderation (UK ICO, France, California AG); image editing now restricted to paid subscribers

Runway Gen-4 Turbo — Runway

Best for: Stylized content, VFX aesthetics, professional ecosystem, real-time avatars

Runway leads in non-photorealistic and stylized video — VFX-oriented aesthetics, abstract content, and artistic directions where other models default to photorealism. Gen-4 Turbo also has the most mature professional ecosystem with motion brushes, scene consistency tools, and a robust API. Runway closed a $315M Series C in February 2026 at a $5.3B valuation.

On March 9, Runway launched Characters — a real-time video agent API built on its GWM-1 world model. Characters generates fully conversational AI avatars from a single reference image with no fine-tuning required. The avatars sustain realistic lip-sync, facial expressions, eye contact, and gesture across extended multi-minute conversations, running at 24fps at 720p in real time. BBC and Silverside are early enterprise partners, with the API available to developers at dev.runwayml.com. Characters targets customer support, interactive training, and branded marketing experiences — a direct play for the enterprise avatar market currently led by HeyGen and Synthesia.

At NVIDIA GTC (March 17, 2026), Runway demoed a research preview of a new real-time video generation model running on NVIDIA Vera Rubin hardware — achieving time-to-first-frame under 100ms for HD video. The demo also revealed that Gen-4.5, Runway’s next commercial model, is being developed and tested on Vera Rubin ahead of its public release; no launch date has been announced. The real-time model is not yet a product, but it establishes the performance target Runway is building toward as Vera Rubin hardware becomes available via cloud providers in H2 2026.

• Max resolution: 1080p (Gen-4 Turbo); 720p real-time (Characters)
• Audio: Supported
• Key features: Motion brushes, style control, API maturity; Characters real-time avatar API (GWM-1)
• Access: From $12/mo
• API: Most mature video generation API available; Characters API at dev.runwayml.com
• Next: Gen-4.5 in development; real-time video model research preview on Vera Rubin hardware (sub-100ms TTF)
• Note: Characters is an enterprise API product built on GWM-1, separate from the Gen-4 Turbo generation pipeline

Pika 2.5 — Pika Labs

Best for: Budget-conscious creators, rapid iteration, social media content

The most accessible entry point to AI video generation. Pika’s strength is speed and volume — generate 20-30 variations of a concept in minutes, then refine. Features like Pikaswaps (face/object replacement) and Pikaffects (style transfer) add creative flexibility at a price point that undercuts every competitor.

• Max resolution: 1080p
• Max duration: 42 seconds
• Audio: Supported
• Key feature: Pikaswaps, Pikaffects, fast batch generation
• Access: From $8/mo (lowest entry price among major models)
• API: Available

Open-Source & Local Generation

The open-source AI video ecosystem has matured significantly, making local generation on consumer hardware a viable option for privacy-conscious creators and developers.

LTX-2.3 — Lightricks

Best for: Local/desktop generation, consumer GPU workflows, high-frame-rate output

The standout for local generation — and now significantly upgraded. Released March 2026, LTX-2.3 is a comprehensive rebuild of the original LTX-2: a new VAE for sharper detail, a 4× larger text connector for better prompt understanding, and an improved HiFi-GAN vocoder for cleaner native audio. The model ships alongside a dedicated desktop video editor, making the entire local pipeline accessible without a ComfyUI node graph.

Key new capabilities: native portrait mode (9:16 up to 1080×1920), last-frame interpolation for seamless clip chaining, and 24/48fps output options alongside the previous frame rates. At GDC this week, NVIDIA announced 2.5× performance gains on RTX 50 Series via NVFP4 quantization, 60% lower VRAM usage, and RTX Video Super Resolution for ComfyUI delivering 4K upscaling 30× faster than competing local alternatives. The new ComfyUI App View strips the node-graph interface into a simplified prompt-in/video-out UI for non-technical users.

• Max resolution: 4K native (true 4K, not upscaled)
• Max duration: 20 seconds
• Frame rate: Up to 50fps (24/48fps options also available)
• Audio: Native synchronized audio (improved HiFi-GAN vocoder)
• Portrait mode: Yes (9:16, up to 1080×1920)
• Hardware: Runs on GPUs with 12GB+ VRAM; optimized for RTX 50 Series (2.5× faster via NVFP4)
• Integration: ComfyUI native; standalone desktop video editor (shipped March 2026)
• License: Apache 2.0 (free for companies under $10M revenue; commercial license required above that threshold)

Wan 2.2 — Alibaba (Wan-AI)

Best for: Image-to-video, MoE architecture, research and experimentation

Alibaba’s Wan 2.2 series introduces Mixture-of-Experts (MoE) architecture to video generation — using specialized experts for different stages of the generation process. Available in both text-to-video (T2V) and image-to-video (I2V) variants.

• Max resolution: 720p–1080p
• Architecture: MoE (high-noise expert + low-noise expert)
• Variants: Wan2.2-T2V-A14B, Wan2.2-I2V-A14B
• License: Open source

Other Notable Open-Source Models

• SkyReels V1 (Skywork AI) — Cinematic-quality with strong facial animation and camera movement
• Mochi 1 — High-fidelity short video with strong prompt alignment
• HunyuanVideo (Tencent) — Solid image-to-video with coherent motion
• MAGI-1 — Long-form video synthesis capabilities
• Helios (Peking University / ByteDance / Canva) — 14B autoregressive diffusion model; 19.5fps real-time generation on a single NVIDIA H100; capable of minute-scale video; Apache 2.0 license. Released March 2026. Notable for real-time throughput on a single accelerator.

How to Choose: A Routing Framework

The right model depends on the shot, not the project. Here’s a practical decision framework:

Need broadcast-ready 4K? → Kling 3.0 or Veo 3.1

Need a free starting point? → Veo 3.1 via Google Vids (10 free clips/month, any Google account)

Need character consistency across shots? → Seedance 2.0 Pro (if accessible) or Luma Ray 3.14

Need stylized / VFX aesthetic? → Runway Gen-4 Turbo

Need professional production volume at scale? → Luma Ray 3.14 (4× faster, 3× cheaper than previous Ray)

Need volume at low cost? → Pika 2.5

Need cheapest API? → Grok Imagine ($4.20/min)

Need local generation / privacy? → LTX-2.3 via ComfyUI or desktop editor

Need real-time interactive avatars? → Runway Characters (GWM-1)

Need multi-shot narrative? → Seedance 2.0 Pro (if accessible) or Luma Ray 3.14

Need massive distribution? → Grok Imagine (500M+ X users)

Most professional workflows now use 2-3 models per project, routing different shots to different engines based on the specific requirements of each scene.

What’s Coming

• Runway Gen-4.5 — Previewed on NVIDIA Vera Rubin hardware at GTC (March 2026); no public launch date announced. Expected to be Runway’s highest-performance commercial model to date
• NVIDIA Vera Rubin cloud deployment — AWS, Google Cloud, Microsoft Azure, and OCI all confirmed H2 2026 availability. Vera Rubin delivers 10× lower inference token cost versus Blackwell — the number that will reshape per-second AI video pricing across all major cloud platforms
• DLSS 5 — NVIDIA’s neural rendering technology, launching Fall 2026. Explicitly positioned for filmmaking and VFX beyond gaming; uses generative AI to infuse photoreal lighting and materials anchored to source 3D geometry
• Blackburn draft AI bill — GOP Senate draft (March 19, 2026) declares AI training on copyrighted works not fair use; targets deepfakes and Section 230. Not yet introduced as legislation; path to passage uncertain
• White House AI framework vs. CLEAR Act — White House (March 2026) takes the opposite position from Blackburn: AI training is not infringement; courts should decide. Bipartisan CLEAR Act (Schiff/Curtis) proposes mandatory training data disclosure without resolving fair use. Three irreconcilable positions now active in Washington simultaneously
• Seedance 2.0 Pro US access — ByteDance launched Dreamina Seedance 2.0 in emerging markets (March 23) while continuing to exclude the US. Next move — lawsuit, licensing deal, or extended deferral — sets precedent for the industry
• Veo 3.1 Fast price cut — Scheduled for April 7, 2026; will compress the entire Veo pricing stack further and likely trigger competitive responses from Runway, Kling, and Luma on API pricing
• OpenAI robotics / world simulation — OpenAI redirected Sora’s compute toward “world simulation for robotics” after shutting the product down. Sora API access continues until September 24; watch for whether any video-adjacent capability resurfaces inside ChatGPT
• Google Vids / Workspace expansion — YouTube export is now live; paid creative tiers (Pro/Ultra) now include Lyria 3 music generation and AI avatars. Further Workspace AI integration expected throughout 2026
• EU AI Act Article 50 — August 2026, requiring machine-readable metadata on all AI-generated content
• Unlimited-length AI video — EPFL’s drift elimination breakthrough (presenting at ICLR 2026) could remove the duration ceiling entirely
• xAI targeting 30-minute video — Announced goal for late 2026, with full-length films targeted for 2027

This page is maintained by RCTV as a public reference. For weekly updates on model releases and industry shifts, see our Weekly Roundup.

Have a correction or update? Contact us at rctv.oxncw@simplelogin.com

CHANGELOG

• Last updated date: Advanced from March 7 to March 13, 2026
• Sora 2 (OpenAI): Added Sora 1 retirement notice (effective March 13, US users); added note on reported ChatGPT integration plans (The Information, March 12) and declining standalone app install figures (−45% MoM, January 2026); updated Disney licensing detail to specify all four brands (Disney, Marvel, Pixar, Star Wars); added Note spec bullet summarizing access changes
• Runway Gen-4 Turbo: Added $315M Series C / $5.3B valuation (February 2026); added two-paragraph description of Runway Characters (launched March 9) — real-time avatar API built on GWM-1, BBC and Silverside as launch partners, available at dev.runwayml.com; updated Best for tagline and spec bullets to reflect Characters alongside Gen-4 Turbo
• LTX-2 → LTX-2.3: Renamed entry to reflect new version; rewrote description to cover the 22B-parameter rebuild (new VAE, 4× text connector, HiFi-GAN vocoder), desktop video editor launch, portrait mode (9:16), last-frame interpolation, and 24/48fps options; updated NVIDIA acceleration figures from “3× / 60%” (CES) to “2.5× / 60%” (GDC RTX 50 Series specific); added RTX Video Super Resolution 30× upscaling stat; added ComfyUI App View simplified UI; updated spec bullets (true 4K native, 50fps, Apache 2.0 commercial licensing threshold)
• Other Notable Open-Source Models: Added Helios (Peking University / ByteDance / Canva) — 14B autoregressive diffusion model, 19.5fps real-time on single H100, Apache 2.0, released March 2026
• How to Choose routing framework: Updated “LTX-2” reference to “LTX-2.3”; added “Need real-time interactive avatars? → Runway Characters (GWM-1)”
• What’s Coming: Added “Sora integration into ChatGPT” item; updated “NVIDIA GTC 2026” from “later this month” to specific March 16–19 date with Jensen Huang keynote detail; all other items unchanged

March 20, 2026

• Last updated date: Advanced from March 13 to March 20, 2026
• Tags: Added regulation tag — regulatory developments are now a recurring weekly topic affecting multiple tracked models
• Runway Gen-4 Turbo: Added third description paragraph covering the GTC real-time video model research preview (sub-100ms TTF on Vera Rubin hardware, March 17) and Gen-4.5 signal (confirmed running on Vera Rubin ahead of public release, no launch date); added Next: spec bullet summarizing both developments
• Seedance 2.0 Pro: Added paragraph noting legislative reinforcement from the Blackburn draft AI bill (March 19) — which, if enacted, would make unauthorized AI training use of copyrighted works categorically not fair use; updated Note: spec bullet to reference the bill
• What’s Coming: Removed “NVIDIA GTC 2026” item (event concluded); added “Runway Gen-4.5” (previewed at GTC); added “NVIDIA Vera Rubin cloud deployment H2 2026” (confirmed by AWS, Google Cloud, Microsoft, OCI; 10× inference cost reduction); added “DLSS 5 Fall 2026” (neural rendering with VFX/filmmaking ambitions beyond gaming); added “Blackburn draft AI bill” (copyright/deepfake provisions); updated Seedance item to note Blackburn bill adds legislative pressure

March 27, 2026

• Last updated date: Advanced from March 20 to March 27, 2026
• Tags: Added luma tag to reflect Luma Ray 3.14 promotion to primary tracked model
• Sora 2 — OpenAI: Removed from active Big Seven tracking — product discontinued March 24, 2026. Section replaced with a brief discontinuation note citing $15M/day burn rate vs. $2.1M lifetime revenue, Disney deal collapse, and OpenAI’s pivot to robotics/world simulation. Model entry retained as a historical reference with strikethrough heading
• Luma Ray 3.14 — Luma AI: Added as new Big Seven entry, replacing Sora. Native 1080p, 4× faster generation, 3× cheaper per-second pricing vs. previous Ray. Ray3 Modify companion tool for hybrid performance/acting workflows. $900M Series C (HUMAIN), new London office. Enterprise deployments via Luma Agents (Publicis, Adidas, Mazda). Promoted from “Models to Watch” list
• Seedance 2.0 Pro: Added paragraph on Dreamina Seedance 2.0 relaunch (March 23) in Africa, South America, Middle East, Southeast Asia — US still excluded. Added paragraph on three-way Washington copyright standoff: Blackburn bill vs. White House AI framework vs. CLEAR Act (Schiff/Curtis). Updated Access and Note spec bullets to reflect Dreamina regional launch
• How to Choose routing framework: Removed “Need realistic physics? → Sora 2”; added “Need professional production volume at scale? → Luma Ray 3.14”; updated “character consistency” and “multi-shot narrative” routes to include Luma Ray 3.14 alongside Seedance as a US-accessible alternative
• What’s Coming: Removed “Sora integration into ChatGPT” (product dead); added “White House AI framework vs. CLEAR Act” (new copyright legislative developments); updated Seedance item to reflect Dreamina emerging-markets launch and US exclusion; added “OpenAI robotics/world simulation” item tracking what comes next from OpenAI in the video-adjacent space

April 4, 2026

• Last updated date: Advanced from March 27 to April 4, 2026
• Sora 2 — OpenAI (discontinued): Added specific shutdown timeline — app and web interface off April 26, 2026; API access continues until September 24, 2026
• Veo 3.1 — Google DeepMind: Major access and pricing update. Added Google Vids free tier (10 clips/month for any Google account, 8 sec at 720p, text-to-video and image-to-video); added Google AI Pro/Ultra features (1,000 clips/month, Lyria 3 music up to 3 min, AI avatars with scene/wardrobe control, YouTube export now live). Added Veo 3.1 Lite developer tier via Gemini API / Google AI Studio ($0.05/sec 720p, $0.08/sec 1080p, <50% cost of Fast tier, same speed). Updated “Best for” tagline, description paragraphs, Access spec, and API spec bullets. Updated Key features bullet to reflect Vids integration
• How to Choose routing framework: Added “Need a free starting point? → Veo 3.1 via Google Vids (10 free clips/month)”
• What’s Coming: Removed “Google Flow + YouTube integration” (YouTube export now live in Google Vids); added “Veo 3.1 Fast price cut April 7”; updated “OpenAI robotics/world simulation” item to include Sora API September 24 deadline; replaced with “Google Vids/Workspace expansion” item for ongoing paid tier rollout