Kling 4.0

Headlines · 5

1. 1d
   Kling 4.0 launches globally with up to 30-second video generation

   Kling AI said Kling 4.0 became fully available on klingai.com on the evening of Oct 15, and parent Kuaishou's shares opened more than 5% higher the next day. The model natively generates up to 30 seconds of video in one pass with long takes and continuous narrative, native stereo audio, up to 10 keyframes, and up to 15 reference items (10 images, 5 videos, 7 subjects), with prompt input raised to 8,000 tokens. Kling says 4K/1080p 10-bit HDR output and 21:9 framing are coming, video extension can reach two minutes, and the model is available through MCP and CLI with enterprise API access to open "soon"; fal said Kling 4.0 is coming soon to its platform.

   fal (X) · 🔥 33
2. 2d
   AI video price war: Vidu Q4 Preview cuts to ¥0.09/second

   Chinese AI video model makers released new flagship versions and slashed prices in late September and early October. On Sept 28, Kuaishou's Kling 4.0 entered beta with native clips of up to 30 seconds and 4K output, alongside a lightweight Kling 4.0 Flash pitched on fast generation and cost-efficiency, though API pricing has not been disclosed; on Oct 8, Shengshu Technology launched Vidu Q4 Preview with support for 15 reference images and 3 reference audio clips, 4K output and a starting price of ¥0.09 per second, with the company estimating up to about five times more output for the same budget. By contrast, ByteDance's new Seedance flagships cost at least 50% more than the previous generation, at ¥46 per million tokens for Seedance 2.0 720P no-reference generation versus ¥70 for Seedance 2.5 at the same setting. The article argues that as one-pass generation success rates rose — up to roughly 90% for Seedance 2.0 per a BOC International research note it cites, versus an earlier industry average of about 20% — the competition is shifting from raw capability toward price-performance and fit with production workflows.

   36氪 人工智能 · 🔥 3
3. 3d
   Vidu Q4 Preview launches from ¥0.09/second as China's video-model trio splits paths

   According to Zhi Dongxi and 36Kr, China's leading video-generation players refreshed their line-ups around the National Day holiday: Kuaishou's Kling AI announced Kling 4.0 on Sept 28, and Shengshu Technology released Vidu Q4 Preview on Oct 8, the first preview of its next flagship video model, priced from ¥0.09 per second. The article says Vidu Q4 Preview centres on expressive character acting, camera language and complex VFX, supports up to 4K output and 16-second single generations, and accepts up to 15 reference images plus three reference audio clips. It also claims the preview overtook Seedance 2.0 to rank third globally on Artificial Analysis, with MaaS image-to-video pricing of ¥0.59/s at 720p, ¥0.75/s at 1080p and ¥2.43/s at 4K, described as the lowest in the industry.

   智东西 · 🔥 0
4. 4d
   Kling teases Kling 4.0 ahead of LA Tech Week appearance

   Kling AI said it will appear at LA Tech Week 2026 on Oct 14 and teased that its next video-generation model, Kling 4.0, is coming soon. The event runs 16:00–19:00 at Met Her at a Bar in Santa Monica, where guests from Kling, partner Oxen AI and Obsidian Studio will share a roundtable covering model development, platform integration and professional content production. The report says observers are watching for improvements in motion coherence, instruction following and long-shot storytelling, but Kling has not published benchmarks or a firm launch date.

   AIbase AI新闻 · 🔥 0
5. 4d
   Vibe Video: code-rendered clips squeeze Kling 4.0 on two fronts

   After Anthropic released Claude Opus 5.5, creators began using it — with Playwright and FFmpeg — to turn code-written HTML, Canvas, Three.js and GSAP animations into finished videos, a workflow the article calls "Vibe Video." Its strengths are deterministic, addressable frames and low cost (Opus 5.5 API at $4 per million input tokens and $20 per million output tokens), but it cannot render photoreal faces or simulate physics and cannot take reference video as input. On the professional side, Seedance 2.5 offers native 30-second clips and up to 50 multimodal references, Kuaishou's Kling 4.0 added 10-bit HDR, up to 15 reference assets and up to 10 keyframes in late September, and MiniMax H3 is a 33B open multimodal model at 2K/24fps with synchronized audio and video. The article argues general LLMs are capturing the planning stage while dedicated models become rendering engines, leaving Kling 4.0 squeezed between Seedance 2.5 and open-source H3.

   36氪 人工智能 · 🔥 0

Experience and discussion from the community

Share my Kling 4.0 experienceAsk about Kling 4.0