Latest month in the catalog
New AI video models: November 2026
4 AI video models are dated November 2026 in Versely’s catalog, from 1 provider: Google (4). The newest is Gemini Omni Flash 1.2, released 5 November 2026.
| Model | Built by | Released | Credits per job |
|---|---|---|---|
| Gemini Omni Flash 1.2variant | 5 November 2026 | 4-148 credits | |
| Gemini Omni Flash 1.2variant | 5 November 2026 | 4-148 credits | |
| Gemini Omni Flash 1.2variant | 5 November 2026 | 4-148 credits | |
| Gemini Omni Flash 1.2 Edit | 5 November 2026 | 11-295 credits |
See November 2026 in the 2026 video timeline, or jump to every month of 2026.
The 2026 video timeline
6 January 2026
5 models · 1 providerLTX shipped 5 video models on 6 January 2026. All 5 have a spec page. Cheapest complete job in the window: 20 credits on LTX 2. Highest output in it: 4K on LTX 2.
- New name on the roster: LTX.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| LTX 2 Retake VideoRegenerate and improve video segments with LTX 2 | LTX | 24-80 credits | — | 3s, 5s, 10s |
| LTX 2Latest video generation with enhanced control | LTX | 20-256 credits | 4K | 6s, 8s, 10s, 12s, 14s, 16s |
| LTX 2 ProProfessional image-to-video with LTXV2 | LTX | 29-192 credits | 4K | 6s, 8s, 10s |
| LTX 2 Text to Video FastFast text-to-video generation with LTXV2 | LTX | 20-256 credits | 4K | 6s, 8s, 10s, 12s, 14s, 16s |
| LTX 2 Text to Video ProProfessional text-to-video with LTXV2 | LTX | 29-192 credits | 4K | 6s, 8s, 10s |
26–30 January 2026
6 models · 2 providersPixverse and Vidu shipped 6 video models between 26 January 2026 and 30 January 2026. Of the 6, 4 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 6 credits on Vidu Q3 Turbo Image to Video. Highest output in it: 1080p on Pixverse 5.6 Image to Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Pixverse 5.6 Image to VideoLatest Pixverse model for converting images to high-quality animated videos | Pixverse | 28-240 credits | 1080p | 5s, 8s, 10s |
| Pixverse 5.6 Text to VideoGenerate videos directly from text prompts with Pixverse 5.6 advanced capabilities | Pixverse | 28-240 credits | 1080p | 5s, 8s, 10s |
| Vidu Q3 Image to VideoTransform static images into dynamic videos with Vidu Q3 technology | Vidu | 23-67 credits | 1080p | 5s, 10s, 15s |
| Vidu Q3 Turbo Image to VideovariantThe fast tier of Vidu Q3 at half the price: animates a still image with native audio, dialogue and sound effects. Any length from… | Vidu | 6-99 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Vidu Q3 Turbo Text to VideovariantThe fast tier of Vidu Q3 at half the price: text to video with native audio, dialogue and sound effects. Any length from 1 to 16… | Vidu | 6-99 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Vidu Q3 VideoGenerate high-quality videos from text prompts with Vidu Q3 engine | Vidu | 23-67 credits | 1080p | 5s, 10s, 15s |
1–5 February 2026
19 models · 2 providersByteDance and Kling shipped 19 video models between 1 February 2026 and 5 February 2026. Of the 19, 8 have a spec page and 11 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 20 credits on DreamActor V2. Highest output in it: 4K on Kling Video V3 4K Image to Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| DreamActor V2AI-powered face reenactment model that transfers facial expressions and head movements from a driving video to a reference image | ByteDance | 20-480 credits | — | — |
| Kling O3 Pro Image to VideoKling O3 Pro image-to-video with advanced reasoning-enhanced generation and camera controls | Kling | 56-168 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Pro Reference to VideovariantKling O3 Pro reference-to-video for character-consistent generation using reference images | Kling | 56-168 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Pro Text to VideovariantKling O3 Pro text-to-video with reasoning-enhanced generation, camera controls, and audio | Kling | 56-168 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Pro Video to Video EditvariantKling O3 Pro video-to-video editing with reasoning-enhanced prompt-based modifications | Kling | 68 credits | — | — |
| Kling O3 Pro Video to Video ReferencevariantKling O3 Pro video-to-video reference-based editing for style and character transfer | Kling | 68-202 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Standard Image to VideoKling O3 Standard image-to-video with reasoning-enhanced generation | Kling | 45-135 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Standard Reference to VideoKling O3 Standard reference-to-video for character-consistent generation | Kling | 45-135 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Standard Text to VideovariantKling O3 Standard text-to-video with reasoning-enhanced generation | Kling | 45-135 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling O3 Standard Video to Video EditvariantKling O3 Standard video-to-video editing with prompt-based modifications | Kling | 51-1210 credits | — | — |
| Kling O3 Standard Video to Video ReferencevariantKling O3 Standard video-to-video reference-based editing for style transfer | Kling | 51-152 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 4K Image to VideovariantKling V3 4K image-to-video - cinema-grade resolution with advanced camera controls, audio generation, and element composition | Kling | 168-504 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 4K Text to VideovariantKling V3 4K text-to-video - cinema-grade resolution with advanced camera controls, audio generation, and multi-prompt support | Kling | 168-504 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 Pro Image to VideovariantKling V3 Pro image-to-video generation with camera controls, audio generation, and element composition | Kling | 34-101 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 Pro Motion ControlKling V3 Pro motion control - transfer motion from a driving video to a reference image at pro-tier quality | Kling | 34-807 credits | 1080p | — |
| Kling Video V3 Pro Text to VideoKling V3 Pro text-to-video generation with advanced camera controls, audio generation, and multi-prompt support | Kling | 34-101 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 Standard Image to VideoKling V3 Standard image-to-video generation with camera controls and element composition | Kling | 26-76 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling Video V3 Standard Motion ControlKling V3 Standard motion control - transfer motion from a driving video to a reference image | Kling | 26-605 credits | 720p | — |
| Kling Video V3 Standard Text to VideovariantKling V3 Standard text-to-video generation with camera controls and multi-prompt support | Kling | 26-76 credits | — | 3s, 4s, 5s, 6s, 7s, 8s |
12 February 2026
6 models · 1 providerByteDance shipped 6 video models on 12 February 2026. Of the 6, 2 have a spec page and 4 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 18 credits on Seedance 2.0 Fast. Highest output in it: 4k on Seedance 2.0.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Seedance 2.0Seedance 2.0 generates Hollywood-grade cinematic videos from text prompts with native audio-visual synchronization,… | ByteDance | 22-1639 credits | 4k | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 FastvariantSeedance 2.0 Fast generates cinematic videos from text prompts with native audio-visual synchronization, director-level camera… | ByteDance | 18-146 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Fast Image to VideovariantSeedance 2.0 Fast generates cinematic videos from reference images and text prompts with native audio-visual synchronization and… | ByteDance | 39-146 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Fast Reference to VideoSeedance 2.0 Fast Reference to Video generates cinematic videos from reference images, videos, and audio inputs with native… | ByteDance | 39-146 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Image to VideovariantSeedance 2.0 generates Hollywood-grade cinematic videos from reference images and text prompts with native audio-visual… | ByteDance | 22-934 credits | 4k | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Reference to VideovariantSeedance 2.0 Reference to Video generates cinematic videos from reference images, videos, and audio inputs with native… | ByteDance | 44-1867 credits | 4k | 4s, 5s, 6s, 7s, 8s, 9s |
5 March 2026
5 models · 1 providerLTX shipped 5 video models on 5 March 2026. Of the 5, 3 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 16 credits on LTX 2.3 Extend Video. Highest output in it: 4K on LTX 2.3 Image to Video Pro.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| LTX 2.3 Extend VideovariantExtend an existing video — the model continues motion/action past the current end (or before the current start). Takes a source… | LTX | 16-160 credits | — | 2s, 4s, 6s, 8s, 10s, 12s |
| LTX 2.3 Image to Video ProPro-quality image-to-video generation. Animates a still image with a prompt. Supports 1080p/1440p/2160p, 6-20s duration… | LTX | 29-192 credits | 4K | 6s, 8s, 10s |
| LTX 2.3 Retake VideoRetake a segment of an existing video. Takes a source video_url + prompt describing desired changes (e.g. "change flower to red… | LTX | 16-160 credits | — | 2s, 4s, 6s, 8s, 10s, 12s |
| LTX 2.3 Text to Video FastFast text-to-video generation. Generates a video directly from a text prompt at 1080p/1440p/2160p, 6-20s duration, with optional… | LTX | 20-256 credits | 4K | 6s, 8s, 10s, 12s, 14s, 16s |
| LTX 2.3 Text to Video ProvariantPro-quality text-to-video generation. Generates a video directly from a text prompt at 1080p/1440p/2160p, 6-20s duration, with… | LTX | 29-192 credits | 4K | 6s, 8s, 10s |
30 March 2026
6 models · 1 providerPixverse shipped 6 video models on 30 March 2026. Of the 6, 4 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 5 credits on Pixverse V6 Image to Video. Highest output in it: 1080p on Pixverse Effects.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Pixverse EffectsAdd special effects to videos with Pixverse | Pixverse | 12-64 credits | 1080p | 5s, 8s, 10s |
| Pixverse Image to VideovariantConvert images to videos with Pixverse V5.5 | Pixverse | 12-64 credits | 1080p | 5s, 8s, 10s |
| Pixverse Text to VideoGenerate videos from text with Pixverse V5.5 | Pixverse | 12-64 credits | 1080p | 5s, 8s, 10s |
| Pixverse TransitionCreate smooth transitions between video clips | Pixverse | 12-64 credits | 1080p | 5s, 8s, 10s |
| Pixverse V6 Image to VideovariantPixVerse V6 image-to-video. Animates a still image with strong motion and prompt control, optional audio and multi-clip, up to… | Pixverse | 5-29 credits | 1080p | 5s, 8s |
| Pixverse V6 Text to VideoPixVerse V6 text-to-video. Generates video from a text prompt with strong motion and prompt control, optional audio and… | Pixverse | 5-29 credits | 1080p | 5s, 8s |
31 March – 6 April 2026
5 models · 2 providersGoogle and Wan shipped 5 video models between 31 March 2026 and 6 April 2026. Of the 5, 4 have a spec page and 1 is folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 8 credits on VEO 3.1 Lite. Highest output in it: 4K on VEO 3.1 Lite.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| VEO 3.1 LitevariantVEO 3.1 Lite is the most cost-effective model in the VEO 3.1 family for high-volume video generation, supporting text-to-video… | 8-61 credits | 4K | 4s, 6s, 8s | |
| Wan 2.7 Image to VideoWan 2.7 animates images with three modes: first-frame to video, first-and-last-frame interpolation, or video continuation, with… | Wan | 8-90 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 2.7 Reference to VideoWan 2.7 reference-to-video — generate videos from up to 5 reference images and/or videos, with optional first frame and voice… | Wan | 10-72 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 2.7 Text to VideoWan 2.7 generates high-fidelity videos from text prompts with strong motion consistency, optional custom audio input, and… | Wan | 8-90 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 2.7 Video EditWan 2.7 video editing — modify a source video using prompts and an optional reference image for character, clothing, or style… | Wan | 10-72 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
26 April 2026
4 models · 1 providerAlibaba shipped 4 video models on 26 April 2026. Of the 4, 2 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 17 credits on Happy Horse 1.0 Image to Video. Highest output in it: 1080p on Happy Horse 1.0 Image to Video.
- New name on the roster: Alibaba.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Happy Horse 1.0 Image to VideovariantHappy Horse 1.0 animates a first-frame image into video with native synchronized audio, Foley sound effects, and multilingual… | Alibaba | 17-168 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.0 Reference to VideoHappy Horse 1.0 generates videos from up to 9 reference images using character1–character9 placeholders in the prompt, with… | Alibaba | 17-168 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.0 Text to VideovariantHappy Horse 1.0 generates expressive videos from text prompts with native synchronized audio, Foley sound effects, and… | Alibaba | 17-168 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.0 Video EditHappy Horse 1.0 edits a source video using a prompt and up to 5 reference images, with auto/origin audio handling — output capped… | Alibaba | 34-1344 credits | 1080p | — |
1 May 2026
3 models · 1 providerGrok shipped 3 video models on 1 May 2026. Of the 3, 1 has a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 4 credits on Grok Imagine Video 1.5 Image to Video. Highest output in it: 1080p on Grok Imagine Video 1.5 Image to Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Grok Imagine Video 1.5 Image to VideovariantxAI's Grok Imagine Video 1.5 animates a still image with native audio. 480p, 720p or 1080p, any length from 1 to 15 seconds; the… | Grok | 4-150 credits | 1080p | 1s, 2s, 3s, 4s, 5s, 6s |
| Grok Imagine Video 1.5 Reference to VideovariantxAI's Grok Imagine Video 1.5 builds a video from up to 7 reference images, used as style and content guides and addressed in the… | Grok | 4-84 credits | 720p | 1s, 2s, 3s, 4s, 5s, 6s |
| Grok Imagine Video 1.5 Text to VideoxAI's Grok Imagine Video 1.5 turns a prompt into a video with native audio. 480p, 720p or 1080p, any length from 1 to 15 seconds,… | Grok | 4-150 credits | 1080p | 1s, 2s, 3s, 4s, 5s, 6s |
19 May – 1 June 2026
4 models · 2 providersByteDance and Google shipped 4 video models between 19 May 2026 and 1 June 2026. Of the 4, 1 has a spec page and 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 15 credits on Gemini Omni Video. Highest output in it: 4K on Gemini Omni Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Gemini Omni VideoGoogle Gemini Omni multimodal video generation. Accepts a prompt plus optional reference images, source video clips, character… | 15-74 credits | 4K | 4s, 6s, 8s, 10s | |
| Seedance 2.0 MinivariantSeedance 2.0 Mini is a faster, lower-cost tier of Seedance 2.0 — cinematic text-to-video with native audio-visual sync at high… | ByteDance | 22-182 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Mini Image to VideovariantSeedance 2.0 Mini animates a first-frame image into cinematic video with native audio-visual sync — faster and cheaper than full… | ByteDance | 49-182 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.0 Mini Reference to VideovariantSeedance 2.0 Mini generates cinematic video from up to 9 reference images, 3 reference videos, and 3 reference audios… | ByteDance | 49-182 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
9–10 June 2026
3 models · 2 providersBria and Luma shipped 3 video models between 9 June 2026 and 10 June 2026. Of the 3, 2 have a spec page and 1 is folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 12 credits on Luma Ray 3.2. Highest output in it: 1080p on Luma Ray 3.2.
- New name on the roster: Bria.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Luma Ray 3.2variantLuma's Ray 3.2 animates a still image into a cinematic 5 second shot, with an optional last frame to steer where the scene ends.… | Luma | 12-96 credits | 1080p | 5s |
| Luma Ray 3.2Luma's Ray 3.2 turns a written prompt into a cinematic 5 or 10 second shot with film-style camera motion and lighting, from 540p… | Luma | 40-320 credits | 1080p | 5s, 10s |
| Bria Video Background RemovalBria's video background removal cuts the subject out of a clip up to 30 seconds and returns it on a transparent or solid… | Bria | 56-1344 credits | — | — |
17–23 June 2026
5 models · 2 providersAlibaba and Kling shipped 5 video models between 17 June 2026 and 23 June 2026. Of the 5, 3 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 14 credits on Kling 3 Turbo Image to Video. Highest output in it: 1080p on Kling 3 Turbo Image to Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Kling 3 Turbo Image to VideovariantKling 3 Turbo fast image-to-video generation. | Kling | 14-68 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling 3 Turbo Text to VideoKling 3 Turbo fast text-to-video generation. | Kling | 14-68 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.1 Image to VideoHappy Horse 1.1 animates a first-frame image into 1080p video with synchronized native audio and multilingual lip-sync (aspect… | Alibaba | 17-108 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.1 Reference to VideovariantHappy Horse 1.1 turns up to 9 reference images (character1–character9 placeholders) into 1080p video with synchronized native… | Alibaba | 17-108 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Happy Horse 1.1 Text to VideoHappy Horse 1.1 is Alibaba's video model that generates 1080p video with synchronized native audio and multilingual lip-sync from… | Alibaba | 17-108 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
30 June 2026
4 models · 1 providerGoogle shipped 4 video models on 30 June 2026. Of the 4, 1 has a spec page and 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 40 credits on Gemini Omni Flash Image to Video.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Gemini Omni Flash EditGoogle Gemini Omni Flash - conversational video editing (video-to-video) | 50-1200 credits | — | — | |
| Gemini Omni Flash Image to VideovariantGoogle Gemini Omni Flash - animates a still image into video with audio | 40-100 credits | — | 4s, 6s, 8s, 10s | |
| Gemini Omni Flash Reference to VideovariantGoogle Gemini Omni Flash - video with audio from multimodal reference images | 40-100 credits | — | 4s, 6s, 8s, 10s | |
| Gemini Omni Flash Text to VideovariantGoogle Gemini Omni Flash - text-to-video with synchronized native audio | 40-100 credits | — | 4s, 6s, 8s, 10s |
1 August 2026
4 models · 2 providersByteDance and NVIDIA shipped 4 video models on 1 August 2026. Of the 4, 2 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 8 credits on Cosmos 3 Super Image to Video. Highest output in it: 720p on Cosmos 3 Super Image to Video.
- New name on the roster: NVIDIA.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Cosmos 3 Super Image to VideoNVIDIA's Cosmos 3 Super world model animates a still image with physically grounded motion, guided by a text prompt that a… | NVIDIA | 8-28 credits | 720p | 2s, 3s, 4s, 5s, 6s, 7s |
| Seedance 2.5Dreamina Seedance 2.5 generates a native 30-second single-shot video at up to 720p from one text prompt, reasoning about the… | ByteDance | 22-320 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.5 Image to VideovariantAnimate a single still into a native 30-second clip at up to 720p, extending one frame into continuous motion without the drift… | ByteDance | 22-320 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
| Seedance 2.5 Reference to VideovariantGenerate video from up to 50 multimodal references — images, videos and audio — locking a character, set and palette across a… | ByteDance | 67-1114 credits | 720p | 4s, 5s, 6s, 7s, 8s, 9s |
5 August 2026
7 models · 2 providersBlack Forest Labs and MiniMax shipped 7 video models on 5 August 2026. Of the 7, 4 have a spec page and 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 12 credits on Minimax H3 Image to Video. Highest output in it: 2K on Minimax H3 Image to Video.
- New names on the roster: Black Forest Labs, MiniMax.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Flux 3 Extend VideoFLUX.3 continues an existing clip beyond its final frame, generating footage consistent with the original motion and scene… | Black Forest Labs | 82-328 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Flux 3 First Last Frame to VideoFLUX.3 interpolates a smooth, coherent transition between a defined start frame and end frame, with native audio — up to 1080p… | Black Forest Labs | 34-136 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Flux 3 Image to VideovariantFLUX.3 animates a single still image into coherent, natural motion with native audio — up to 1080p and 5–20 seconds | Black Forest Labs | 34-136 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Flux 3 Text to VideoFLUX.3 is Black Forest Labs' frontier video model — generates video with native audio directly from a text prompt, at up to 1080p… | Black Forest Labs | 34-136 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Image to VideovariantMiniMax H3 animates a supplied image into 2K video as the opening frame, or pairs a first and last frame to control a transition… | MiniMax | 12-78 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Reference to VideovariantMiniMax H3 generates 2K video from multimodal references — up to 9 images for subject and style, 3 video clips for motion, and 3… | MiniMax | 12-78 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Text to VideoMiniMax H3 is a frontier video model — generates 2K video from a text prompt alone, in durations from 5 to 15 seconds across six… | MiniMax | 12-78 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
24 August 2026
10 models · 2 providersLTX and Wan shipped 10 video models on 24 August 2026. Of the 10, 3 have a spec page and 7 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 4 credits on Wan 3.0 Image to Video. Highest output in it: 2160p on LTX 2.5 Image to Video Fast.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| LTX 2.5 Image to Video FastvariantSpeed-optimised image-to-video with synchronized native audio. Animates a still image, or interpolates between a start and end… | LTX | 44-480 credits | 2160p | 6s, 8s, 10s, 12s, 14s, 16s |
| LTX 2.5 Image to Video ProvariantQuality-optimised image-to-video with synchronized native audio, for final high-fidelity output. Animates a still image or… | LTX | 58-136 credits | 1080p | 6s, 8s, 10s |
| LTX 2.5 Text to Video FastvariantSpeed-optimised text-to-video with synchronized native audio in a single pass. 720p to 4K, 6-20s (durations past 10s render at… | LTX | 44-480 credits | 2160p | 6s, 8s, 10s, 12s, 14s, 16s |
| LTX 2.5 Text to Video ProQuality-optimised text-to-video with synchronized native audio in a single pass, for final high-fidelity output. 720p or 1080p,… | LTX | 58-136 credits | 1080p | 6s, 8s, 10s |
| Wan 3.0 Image to VideovariantAnimates a still image with Alibaba's Wan 3.0, with native audio. Ranked #1 on the Artificial Analysis image-to-video board at… | Wan | 4-120 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 3.0 Prime Image to VideovariantThe accelerated tier of Wan 3.0 image-to-video: animates a still image with native audio, served faster at a higher per-second… | Wan | 6-168 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 3.0 Prime Reference to VideovariantThe accelerated tier of Wan 3.0 reference-to-video: up to 10 images, 5 video clips and 5 audio clips, or a document or web page,… | Wan | 6-168 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 3.0 Prime Text to VideoThe accelerated tier of Wan 3.0: the same text-to-video model with native audio, served faster at a higher per-second rate. 480p,… | Wan | 6-168 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 3.0 Reference to VideovariantAlibaba's Wan 3.0 builds a video from reference media: up to 10 images, 5 video clips and 5 audio clips, addressed positionally… | Wan | 4-120 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
| Wan 3.0 Text to VideoAlibaba's Wan 3.0 generates video with native audio from a text prompt. Ranked #1 on the Artificial Analysis text-to-video board… | Wan | 4-120 credits | 1080p | 2s, 3s, 4s, 5s, 6s, 7s |
25 August 2026
6 models · 2 providersGoogle and MiniMax shipped 6 video models on 25 August 2026. Of the 6, 1 has a spec page and 5 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 8 credits on Gemini Omni Flash 1.1. Highest output in it: 4K on Gemini Omni Flash 1.1 Edit.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Gemini Omni Flash 1.1 EditGoogle's Gemini Omni Flash 1.1 edits a clip of up to 10 seconds from one plain-language instruction (restyle it, change the… | 12-240 credits | 4K | — | |
| Gemini Omni Flash 1.1variantGoogle's updated Omni Flash animates a still into a 3 to 10 second clip with synchronized audio, with an optional end frame to… | 8-240 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s | |
| Gemini Omni Flash 1.1variantGoogle's updated Omni Flash turns up to 7 reference images (characters, products, places or a style) and a prompt into a 4 to 10… | 16-120 credits | 4K | 4s, 6s, 8s, 10s | |
| Gemini Omni Flash 1.1variantGoogle's updated Omni Flash makes a 3 to 10 second video with synchronized speech, music and sound from a text prompt, now from… | 8-240 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s | |
| Minimax H3 Max Image to VideovariantAnimates a still image with a post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics. Add… | MiniMax | 20-96 credits | 480P | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Max Text to VideovariantA post-trained variant of MiniMax H3, tuned for stronger prompt adherence and better aesthetics, and roughly a third of H3's… | MiniMax | 20-96 credits | 480P | 5s, 6s, 7s, 8s, 9s, 10s |
29 August – 2 September 2026
3 models · 1 providerMiniMax shipped 3 video models between 29 August 2026 and 2 September 2026. Of the 3, 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 10 credits on Minimax H3 Max Turbo. Highest output in it: 1080P on Minimax H3 Max Reference.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Minimax H3 Max ReferencevariantBuilds a new 5 to 15 second scene with generated sound that keeps the people, products or places from up to 9 reference images… | MiniMax | 20-192 credits | 1080P | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Max TurbovariantThe fast, half-price tier of H3 Max (fal's post-trained MiniMax H3): animates a still image into a 5 to 15 second clip with… | MiniMax | 10-96 credits | 1080P | 5s, 6s, 7s, 8s, 9s, 10s |
| Minimax H3 Max TurbovariantThe fast, half-price tier of H3 Max (fal's post-trained MiniMax H3): turns a text prompt into a 5 to 15 second clip with… | MiniMax | 10-96 credits | 1080P | 5s, 6s, 7s, 8s, 9s, 10s |
15–28 September 2026
3 models · 2 providersCreatify and Kling shipped 3 video models between 15 September 2026 and 28 September 2026. Of the 3, 2 have a spec page and 1 is folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 4 credits on Boreal. Highest output in it: 2K on Boreal.
- New name on the roster: Creatify.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| BorealCreatify's Boreal makes product, UGC and presenter videos with synchronized native speech and sound from a prompt, optionally… | Creatify | 4-192 credits | 2K | 5s, 10s, 15s, 20s |
| Kling 4.0 FlashvariantKling 4.0 Flash animates a still image into a 3 to 20 second 720p video with its own sound, using your picture as the first… | Kling | 12-76 credits | 720p | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling 4.0 FlashKling 4.0 Flash is the fast, lower-cost tier of Kling AI's 4.0 video model. It turns a text prompt into a 3 to 20 second 720p… | Kling | 12-76 credits | 720p | 3s, 4s, 5s, 6s, 7s, 8s |
30 September 2026
3 models · 1 providerHeyGen shipped 3 video models on 30 September 2026. Of the 3, 1 has a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 8 credits on HeyGen Video. Highest output in it: 2K on HeyGen Video.
- New name on the roster: HeyGen.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| HeyGen VideovariantHeyGen Video animates your picture as the first frame of a 5 to 15 second clip with generated sound, up to 2K. Built on MiniMax… | HeyGen | 8-72 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
| HeyGen VideovariantHeyGen Video builds a new 5 to 15 second scene with generated sound that keeps the products, people or places from up to 9… | HeyGen | 8-72 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
| HeyGen VideoHeyGen Video is HeyGen's general-purpose video model, built on MiniMax H3 and post-trained by HeyGen. It turns a prompt into a 5… | HeyGen | 8-72 credits | 2K | 5s, 6s, 7s, 8s, 9s, 10s |
5–15 October 2026
4 models · 2 providersKling and Vidu shipped 4 video models between 5 October 2026 and 15 October 2026. Of the 4, 2 have a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 6 credits on Vidu Q4. Highest output in it: 4K on Vidu Q4.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Vidu Q4ShengShu's newest Vidu turns a still image into a 3 to 16 second clip with native audio, dialogue and sound effects, from 540p up… | Vidu | 6-250 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s |
| Vidu Q4 ReferencevariantShengShu's newest Vidu builds a 3 to 16 second clip from up to 12 reference images, keeping the same characters, products and… | Vidu | 6-250 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling 4.0variantKling 4.0 animates your picture into a 3 to 30 second video at 720p or 1080p with its own ambient sound, and an optional end… | Kling | 19-282 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
| Kling 4.0Kling 4.0 is Kling AI's October 2026 video model. It turns a text prompt into a single 3 to 30 second shot at 720p or 1080p with… | Kling | 19-282 credits | 1080p | 3s, 4s, 5s, 6s, 7s, 8s |
16 October 2026
4 models · 2 providersBlack Forest Labs and Versely shipped 4 video models on 16 October 2026. Of the 4, 1 has a spec page and 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 30 credits on Versely Remix Motion Transfer. Highest output in it: 1080p on Flux 3 Max.
- New name on the roster: Versely.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Flux 3 MaxvariantFLUX 3 Max is fal's post-trained upgrade of Black Forest Labs' FLUX 3 video model. It animates a still image, with an optional… | Black Forest Labs | 68-464 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Flux 3 MaxvariantFLUX 3 Max is fal's post-trained upgrade of Black Forest Labs' FLUX 3 video model, tuned for closer prompt following and cleaner… | Black Forest Labs | 68-464 credits | 1080p | 5s, 6s, 7s, 8s, 9s, 10s |
| Versely Remix Motion TransfervariantYour photos move the way the clip does. Add a 4–15 second clip and 1–8 photos. The clip's length and sound are kept. | Versely | 30-604 credits | 1080p | — |
| Versely Remix Object SwapSwap people, products or objects in a clip for the ones in your photos. Add a 4–15 second clip and 1–8 photos. The clip's motion… | Versely | 30-604 credits | 1080p | — |
22–27 October 2026
3 models · 2 providersPixverse and Versely shipped 3 video models between 22 October 2026 and 27 October 2026. Of the 3, 1 has a spec page and 2 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 5 credits on PixVerse V6 Max. Highest output in it: 1080p on PixVerse V6 Max.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| PixVerse V6 MaxvariantPixVerse V6 Max Image to Video animates your picture as the first frame of a 1 to 15 second clip up to 1080p with native sound.… | Pixverse | 5-68 credits | 1080p | 3s, 5s, 8s, 10s, 15s |
| PixVerse V6 MaxvariantPixVerse V6 Max is the top tier of PixVerse's V6 video model (October 2026). It turns a text prompt into a 1 to 15 second clip up… | Pixverse | 5-68 credits | 1080p | 3s, 5s, 8s, 10s, 15s |
| Versely Remix RestyleTurn your clip into another look, from anime to knitted yarn. Add a 4–15 second clip and pick a style. The clip's motion and… | Versely | 30-604 credits | 1080p | — |
5 November 2026
4 models · 1 providerGoogle shipped 4 video models on 5 November 2026. Of the 4, 1 has a spec page and 3 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 4 credits on Gemini Omni Flash 1.2. Highest output in it: 4K on Gemini Omni Flash 1.2 Edit.
| Model | Built by | Credits per job | Max output | Clip lengths |
|---|---|---|---|---|
| Gemini Omni Flash 1.2 EditGoogle's Gemini Omni Flash 1.2 changes a clip of up to 15 seconds from one plain instruction, such as a new setting, weather,… | 11-295 credits | 4K | — | |
| Gemini Omni Flash 1.2variantGoogle's Omni Flash 1.2 animates your still into a clip of up to 15 seconds with synchronized sound, keeping faces, clothes and… | 4-148 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s | |
| Gemini Omni Flash 1.2variantGoogle's Omni Flash 1.2 builds a clip of up to 15 seconds around your reference images of characters, products or places, holding… | 4-148 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s | |
| Gemini Omni Flash 1.2variantGoogle's Omni Flash 1.2 writes a 3 to 15 second video from a text prompt, with characters who speak in sync, plus music and… | 4-148 credits | 4K | 3s, 4s, 5s, 6s, 7s, 8s |
New AI video models by month in 2026
10 of the twelve months carried a video release; the busiest window was 1–5 February 2026, with 19. Each month links to the launch window where it starts.
Who shipped video in 2026
Kling (24), Google (14) and LTX (14) led on volume. SKUs, not quality — four tiers of one model count four times.
| Provider | Models | Spec pages | First | Latest |
|---|---|---|---|---|
| Kling | 24 | 10 | 5 February 2026 | 15 October 2026 |
| 14 | 5 | 31 March 2026 | 5 November 2026 | |
| LTX | 14 | 9 | 6 January 2026 | 24 August 2026 |
| ByteDance | 13 | 4 | 1 February 2026 | 1 August 2026 |
| Pixverse | 10 | 6 | 26 January 2026 | 22 October 2026 |
| Wan | 10 | 6 | 6 April 2026 | 24 August 2026 |
| MiniMax | 8 | 1 | 5 August 2026 | 2 September 2026 |
| Alibaba | 7 | 4 | 26 April 2026 | 23 June 2026 |
| Black Forest Labs | 6 | 3 | 5 August 2026 | 16 October 2026 |
| Vidu | 6 | 3 | 30 January 2026 | 5 October 2026 |
| Grok | 3 | 1 | 1 May 2026 | 1 May 2026 |
| HeyGen | 3 | 1 | 30 September 2026 | 30 September 2026 |
| Versely | 3 | 2 | 16 October 2026 | 27 October 2026 |
| Luma | 2 | 1 | 9 June 2026 | 9 June 2026 |
| Bria | 1 | 1 | 10 June 2026 | 10 June 2026 |
| Creatify | 1 | 1 | 15 September 2026 | 15 September 2026 |
| NVIDIA | 1 | 1 | 1 August 2026 | 1 August 2026 |
What 2026 moved
Firsts, measured against every video model released before them. “New name on the roster” is the provider label in the catalog, not the company — one lab can hold several labels.
- 6 January 2026
- New name on the roster: LTX.
- 26 April 2026
- New name on the roster: Alibaba.
- 9–10 June 2026
- New name on the roster: Bria.
- 1 August 2026
- New name on the roster: NVIDIA.
- 5 August 2026
- New names on the roster: Black Forest Labs, MiniMax.
- 15–28 September 2026
- New name on the roster: Creatify.
- 30 September 2026
- New name on the roster: HeyGen.
- 16 October 2026
- New name on the roster: Versely.
Dates are each model’s released_at value, walked in order and grouped until a window held 3 or more. Credits are what one complete generation costs per the model’s own price matrix; where it states none, the headline rate is shown and the model sits out the cheapest-in-window line.
Other release years
Frequently asked questions
What are the newest AI video models?+
The newest video model in Versely's catalog is Gemini Omni Flash 1.2 from Google, released 5 November 2026. November 2026 is the latest month with video releases: 4 video models from Google.
How many AI video models were released in 2026?+
Versely's catalog carries 126 video models with a 2026 release date, from 17 providers, arriving in 24 launch windows between 6 January 2026 and 5 November 2026.
What was the biggest AI video launch of 2026?+
1–5 February 2026, with 19 video models from ByteDance and Kling. Of the 19, 8 have a spec page and 11 are folded into a parent model's page as tier or mode variants. Cheapest complete job in the window: 20 credits on DreamActor V2. Highest output in it: 4K on Kling Video V3 4K Image to Video.
Which company released the most AI video models in 2026?+
Kling, with 24 of the 126 video models dated 2026 — first on 5 February 2026, most recently on 15 October 2026. Google shipped 14, LTX shipped 14, ByteDance shipped 13.
What changed in AI video generation in 2026?+
Measured against everything the catalog carried before it: New name on the roster: LTX; New name on the roster: Alibaba; New name on the roster: Bria.
Run any 2026 video model in Versely
The all-in-one AI studio for creators. 60+ models for video, image, voice, music and lipsync, in your browser or on your phone.
One account for the web and iPhone.