MiniMax H3 Image Highspeed
MiniMax H3 Image Highspeed is the faster API variant of MiniMax’s H3-Image generation model. It uses the same API parameters and limits as the standard variant. The H3-Image family is described by…
MODEL DIRECTORY
New releases, in one place. Explore models by their publication date.
MiniMax H3 Image Highspeed is the faster API variant of MiniMax’s H3-Image generation model. It uses the same API parameters and limits as the standard variant. The H3-Image family is described by…
MiniMax H3 Image is an open-weight image generation and editing model built on MiniMax H3. It supports text-to-image generation, reference-based generation, and image editing with up to 16 reference…
MiniMax M3.1 Flash is a multimodal mixture-of-experts model positioned for agentic workflows, software engineering, computer use and cybersecurity. MiniMax identifies the earlier anonymous model Space…
MiniMax Music 3.0 is an open-weights music-generation model intended for production-oriented song creation. Given a creative description and optional lyrics, it can compose, arrange, perform and…
MiniMax H3 is a general-purpose multimodal generation model focused on video with synchronized native stereo audio. It understands combined text, image, video and audio context and supports…
Music-3.0 is MiniMax’s music-generation model. It takes a creative concept and optional lyrics and can compose, arrange, perform, and produce a complete song in one generation. MiniMax describes the…
Release date: June 1, 2026. MiniMax positions M3 as a natively multimodal model for coding and agentic work, with a context window of up to 1 million tokens. (minimax.io) Accepts text, image and video…
MiniMax-M2.7-highspeed is the faster API variant of MiniMax's M2.7 language model, aimed at agentic and productivity workloads. MiniMax states that the standard and high-speed versions produce…
MiniMax-M2.7 is a language model oriented toward agentic workflows and real-world productivity. MiniMax describes it as its first model to participate deeply in its own development, including building…
MiniMax Music 2.5+ is a music-generation model presented as an extension of Music 2.5 with instrumental music generation. The official announcement was published on March 4, 2026. (minimax.cn)…
M2.5-Lightning is the faster serving version of MiniMax M2.5, announced on February 12, 2026. MiniMax states that the two versions have identical capabilities but different speeds: Lightning is…
MiniMax-M2.5 is an open-weight language model designed for coding, tool-using agents, search and office productivity. MiniMax announced it on February 12, 2026. (minimax.io) Plans and develops…
MiniMax Speech 2.8 is a text-to-speech model family focused on natural, expressive synthesized speech. MiniMax announced it on January 23, 2026; the supplied release identifier is Speech-2.8. The…
MiniMax-M2.1 is an open-weight language model focused on complex real-world tasks, particularly multilingual software development and agentic workflows. MiniMax announced it on December 23, 2025.…
VTP-Large-f16d64 is a pretrained visual tokenizer and image-feature-extraction model from the VTP research project by MiniMax and Huazhong University of Science and Technology. VTP jointly trains…
VTP-Base-f16d64 is the Base checkpoint of MiniMax’s VTP visual-tokenizer research project. It learns visual representations through joint image–text contrastive, self-supervised and reconstruction…
VTP-Small-f16d64 is the Small checkpoint in the VTP visual-tokenizer research project involving MiniMax and Huazhong University of Science and Technology. It is intended for image feature extraction…
MiniMax-Hailuo-2.3 is a video-generation model built on Hailuo 02, released on October 28, 2025. It accepts text or image inputs and generates short videos. MiniMax positions it for high visual…
MiniMax-M2 is a text-generation mixture-of-experts model designed for coding and agent workflows. MiniMax released it on October 27, 2025. The model has 230 billion total parameters, with 10 billion…