P-Video-2 Pro (Quality) and P-Video-2 Pro (Speed) by @PrunaAI tie each other for #2 on Design Arena's Image to Video leaderboard with an Elo of 1325. Based on MiniMax H3 by @MiniMax, P-Video-2 Pro (Quality) generates in 8.0 seconds, while P-Video-2 Pro (Speed) has an 4.5-second generation time, placing it on the Pareto frontier of Preference vs Speed. Congratulations to the entire @PrunaAI team!

Introducing P-Video-2-Pro-Avatar, based on @MiniMax_AI H3 ! Turn a single portrait into a realistic talking video with natural expressions and accurate lip sync. And for launch, it's 50% off for the first two weeks, until November 5 at 18:00 CET! • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: $0.02/s at 480p · $0.04/s at 768p • 𝗦𝗽𝗲𝗲𝗱: ~0.97 s at 480p · ~2.2 s at 768p per second of output video • 𝗜𝗻𝗽𝘂𝘁: One portrait with a text script or uploaded audio • 𝗩𝗼𝗶𝗰𝗲𝘀: 30 voices across 10 languages • 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 1s–3min at 24 fps, in 480p or 768p • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: Voice delivery, scene motion, seed, and prompt upsampling One image, two ways to bring it to life. Use your own audio or generate speech directly from text. Available via our inference partners @replicate, @eachlabs, @Cloudflare, @scenario_gg, @wavespeed_ai, @WiroAI, Sociaro, @TellersAI, and @togethercompute. 📚 Model docs: docs.api.pruna.ai/guides/mod… 🧩 Try the model through the API or Playground: dashboard.pruna.ai/login

This is directionally consistent with our internal data @cognition. Many tasks within software engineering are now "intelligence saturated." Once any model can do the task well, cost and speed are all that matter.

Introducing P-Video-2-Pro-Reference based on @MiniMax_AI H3! 🎬 Combine images, videos, and audio references to guide how your video looks, moves, and sounds. Keep characters consistent, transfer motion, and bring different visual elements together in a single generation. • 𝗜𝗻𝗽𝘂𝘁: Text prompt with image and/or video references, plus optional audio • 𝗥𝗲𝗳𝗲𝗿𝗲𝗻𝗰𝗲𝘀: Up to 9 images, 3 videos, and 3 audio files • 𝗗𝘂𝗿𝗮𝘁𝗶𝗼𝗻: 5–15s at 480p or 768p • 𝗣𝗿𝗶𝗰𝗶𝗻𝗴: Output starting at $0.015/s in Cost mode, with reference inputs billed separately • 𝗖𝗼𝗻𝘁𝗿𝗼𝗹: First and last frames, seed, aspect ratio, and prompt upsampling Two modes: Speed and Cost. Choose the trade-off that fits your workflow. Available via our inference partners @Cloudflare, @scenario_gg, @replicate, @WiroAI, @TellersAI, @eachlabs, @wavespeed_ai, @inference_sh, @_segmind, @togethercompute, @EdenAIco, and @runware Validated by our benchmark partners @datapointai, @RapidataAI, and @DesignArena 📚 Model docs: docs.api.pruna.ai/guides/mod… 🧩 API: dashboard.pruna.ai/login

Over the last few months at @river_ai_inc we’ve developed what we believe is the best system in the world for building your own internal custom models, driven by 10 years of experience training top models at DeepMind, OpenAI and xAI. In order to best support our customers, we’ve decided to do something radical: We also deploy our API on-prem on your compute cluster, and if you don’t have compute we will help you find it. Again and again we’ve seen that custom models designed for your own internal workflows outperform top frontier models on performance, at a fraction of the cost (1 percent or less). We’re just at the beginning of the custom model era, but its already clear that in the future more than 99% of LLM tokens will be generated on efficient custom models. The economics of it are just too powerful, and it’s far easier than people think once you have the right tools in place. The reason why small models will dominate is due to the physics of deep learning: A general model that can do everything needs more capacity and training it on the whole distribution of all tasks is more challenging, so the model will be larger and more expensive, and wont perform perfectly on every task. A small model trained on a targeted domain usually outperforms it.

Text-to-Video: P-Video-2-Pro is now one of the strongest model families on the @DesignArena leaderboard. Three P-Video-2-Pro modes rank near the top: • Cost: #4 · 1321 Elo • Quality: #5 · 1304 Elo • Speed: #7 · 1294 Elo And on the Preference × Speed benchmark, Pruna makes up 4 of the 5 models on the high-preference section of the Pareto frontier. All three P-Video-2-Pro modes sit on the frontier, offering different trade-offs between preference and generation time. Cost also lands on the Preference × Price Pareto frontier, starting at just $0.01/s. One model, three modes. Depending on whether you want to optimise for cost, speed, or quality. Benchmark by @DesignArena 📚 Documentation: docs.api.pruna.ai/guides/mod… 🧩 API: dashboard.pruna.ai/login 🥇 P-Bench: huggingface.co/spaces/PrunaA…

How does P-Video-2-Pro perform across quality, speed, and cost? Across its modes, it lands on the Pareto frontiers. For the scored 768p Pro variants, the P-Bench data gives: Text-to-Video • Quality: 1022 Elo · 8.34s • Speed: 1011 Elo · 4.04s • Cost: 1011 Elo · 10.17s Image-to-Video • Quality: 1013 Elo · 9.27s • Speed: 994 Elo · 3.00s • Cost: 994 Elo · 10.76s Three modes, each optimised for a different tradeoff: Quality, Speed, or Cost. Across them, P-Video-2-Pro sits on the preference × speed and preference × price Pareto frontiers. 🥇 Full benchmark: huggingface.co/spaces/PrunaA…

P-Video-2-Pro (Cost) lands on the Preference × Price Pareto frontier on @DesignArena, with pricing starting at just $0.01/s. That holds for both Text-to-Video and Image-to-Video, putting Cost among the strongest price–preference tradeoffs on the benchmark. At $0.01/s for 480p and $0.025/s for 768p, it’s the cheapest P-Video-2-Pro mode, while still averaging around 10 seconds per generation, nearly 10× faster than the average video model.

.@PrunaAI has reshaped the quality-cost frontier by dropping the price for P-Video-2 Pro to just $0.01/sec!