Skip to content

Companies & models

MiniMax Latest news

Follow MiniMax models and products: M-series models, voice and multimodal capabilities, open releases, and commercial growth.

12 picksPast 30 days: 0 itemsTotal: 55 items

Updated

Key moments

Since 2021
  1. ProductHailuo AI video generation launches
  2. ModelMiniMax-01 released as open weights
  3. ModelMiniMax-M1 open reasoning model released
  4. ModelHailuo 02 video model released
  5. ModelMiniMax-M2 released
  6. ModelMiniMax releases M2.5 model with 80.2% on SWE-Bench Verified
  7. ModelMiniMax releases open-weight MiniMax-M2.7 with agent and coding gains
  8. ModelMiniMax M3 releases with 1M context, native multimodality and sparse attention
  9. ModelMiniMax releases M3-MXFP8, a 1M-context native multimodal model on Hugging Face
  10. ModelMiniMax H3 releases open-weight omni-modal video model with native stereo audio

MiniMax top picks

Aug 12WedItems 1–12
  1. MiniMax Blog62

    MiniMax releases Music 3.0, an open-weights model for full-length songs

    MiniMax introduces Music 3.0, a music generation model that composes, arranges, performs, and produces a complete song from a creative concept and optional lyrics. The post describes an eight-layer RVQ tokenizer, a Hybrid-LM pairing an 8B Global LLM with a 0.6B Local LLM, and a flow-matching and Flow-VAE audio renderer. It says songs can run up to five minutes and that the model focuses on creative intent, arrangement, and vocal naturalness.

    Why it matters: The post explains how the model's pipeline targets structure, acoustic detail, and vocal realism, which helps readers judge where open-weights music generation stands.

Jul 30Thu
  1. MiniMax Blog72

    MiniMax H3 unifies text, image, video, and audio generation in one model

    MiniMax launches H3, a general-purpose multimodal generation model that understands text, images, video, and audio as unified context. It generates video up to 15 seconds at 2K resolution with native stereo sound, and the company says model weights will be opened in the coming days, subject to applicable laws and regulations. MiniMax also says H3 is priced below mainstream models at 2K and 768p.

    Why it matters: The post explains how a unified multimodal design and training choices enable 2K video with native stereo sound, useful for comparing against closed video generators.

Jul 28Tue
  1. MiniMax · new models on Hugging Face76

    MiniMax H3 releases open-weight omni-modal video model with native stereo audio

    MiniMax released H3, an open-weights omni-modal model that generates video with native stereo audio up to 2K and 15 seconds. The system combines H3-Context-IR preprocessing, the H3-Base generator at 768p, and H3-Regenerate-2K for 2K output, with the Context-IR and 2K modules available only through API.

    Why it matters: The source details a three-module pipeline and open weights with deployment paths, showing how a video model is served and reproduced locally.

Jun 2Tue
  1. MiniMax · new models on Hugging Face78

    MiniMax releases M3-MXFP8, a 1M-context native multimodal model on Hugging Face

    MiniMax published MiniMax-M3-MXFP8, an MXFP8 quantized variant of its native multimodal M3 model with 1M context, about 428B total parameters and about 23B activated parameters. M3 adds MiniMax Sparse Attention, which the source says yields 9× prefill and 15× decode speedups over M2 at 1M context. The model supports three thinking modes (enabled, adaptive, disabled) via the thinking parameter and can be served with SGLang, vLLM, or Transformers.

    Why it matters: The release pairs sparse attention for 1M-token contexts with reported prefill and decode speedups over M2, useful for judging long-context serving costs.

  2. MiniMax · new models on Hugging Face68

    MiniMax releases M3, a native multimodal model with 1M context

    MiniMax has released MiniMax-M3, a native multimodal model with a 1M-token context window, roughly 428B total parameters, and about 23B activated parameters. The model introduces MiniMax Sparse Attention, which the source says delivers 9× prefill and 15× decode speedups over M2 at 1M context. M3 supports enabled, adaptive, and disabled reasoning modes through the thinking parameter, and weights are available on Hugging Face.

    Why it matters: The source gives concrete attention-efficiency figures and three reasoning modes, which helps readers judge long-context cost against deployment choices.

May 31Sun
  1. MiniMax Blog82

    MiniMax M3 releases with 1M context, native multimodality and sparse attention

    MiniMax released M3, an open-weight model with a 1M-token context window, native image and video input, and desktop operation support. The post credits a new sparse attention architecture, MSA, for long-context gains, reporting over 9x prefilling and over 15x decoding speedups and 59.0% on SWE-Bench Pro. The API and MiniMax Code are available now, with the technical report and open weights promised within 10 days.

    Why it matters: The post pairs a new sparse attention design with benchmark figures and a 1M-token context window, letting readers judge the architecture's practical effect on long-context work.

May 26Tue
  1. MiniMax Blog67

    MiniMax Agent Team Adds Parallel Multi-Agent Collaboration for Long Tasks

    MiniMax has upgraded its Agent, renamed Mavis, and introduced Agent Teams that run multiple role-based Agents in parallel on desktop. The team uses Leader, Worker, and Verifier roles so complex tasks can be split, checked, and reported at key checkpoints, and it merges TokenPlan and Agent Plan into one subscription with credits shared between Agent and API. The post also discusses the added token, handoff, and retry costs of multi-Agent work, and says the Agent will be open-sourced alongside MiniMax M3.

    Why it matters: The post explains why multi-Agent helps long tasks and where its verification, token, and aggregation costs come from, useful for judging when a team setup beats a single Agent.

May 25Mon
  1. MiniMax Blog67

    MiniMax Explains Why Its Model Failed to Output Certain Rare Chinese Tokens

    MiniMax says the M2 series could not generate the rare token "嘉祺" in names like Ma Jiaqi, and its investigation traced the cause to post-training. The company found the token was learned in pretraining, but low coverage of rare tokens in post-training data caused lm_head vectors to drift. Adding synthetic full-vocabulary repetition data restored generation for these tokens and reduced Japanese-to-Russian mixing from 47% to 1%.

    Why it matters: The post traces a specific token failure through tokenizer, embedding, and lm_head checks, showing a reusable way to diagnose post-training generation problems.

Apr 8Wed
  1. MiniMax · new models on Hugging Face78

    MiniMax releases open-weight MiniMax-M2.7 with agent and coding gains

    MiniMax has released MiniMax-M2.7 on Hugging Face, describing it as its first model to participate in its own evolution. The source reports 56.22% on SWE-Pro, 46.3% on Toolathon, and 62.7% on MM ClawBench, and says an internal version autonomously optimized a programming scaffold over 100+ rounds for a 30% performance improvement.

    Why it matters: The source ties its benchmark claims to a self-evolution process and a named comparison set, which helps readers weigh how the reported gains were achieved.

Mar 17Tue
  1. MiniMax Blog63

    MiniMax M2.7 takes part in its own model and harness evolution

    MiniMax says M2.7 is its first model to deeply participate in its own evolution, building agent harnesses and running reinforcement learning experiment workflows. The post reports 56.22% on SWE-Pro, 55.6% on VIBE-Pro, 57.0% on Terminal Bench 2, and a 30% improvement on an internal evaluation set after more than 100 autonomous optimization rounds. It also states that M2.7 handles 30%-50% of its research team's workflow, though human researchers still make critical decisions.

    Why it matters: The post ties M2.7's self-evolution claims to specific benchmark numbers and workflow details, helping readers judge how much of the iteration loop is autonomous.

Feb 13Fri
  1. MiniMax Blog62

    MiniMax details Forge, a scalable agent RL framework behind M2.5

    MiniMax describes Forge, its internal reinforcement learning framework for training real-world agents, which was used during the development of MiniMax M2.5. The post explains a Windowed FIFO scheduler, prefix tree merging that the post says yields a 40x training speedup, and CISPO-based training across more than one hundred thousand agent scaffolds and environments.

    Why it matters: The post details how the Forge framework balances throughput, stability, and agent flexibility, with concrete scheduling and prefix-merging methods for training agent RL at scale.

Feb 12Thu
  1. MiniMax · new models on Hugging Face88

    MiniMax releases M2.5 model with 80.2% on SWE-Bench Verified

    MiniMax has released M2.5, which it says reaches 80.2% on SWE-Bench Verified and 76.3% on BrowseComp with context management. The company reports 37% faster end-to-end runtime than M2.1 on SWE-Bench Verified and prices M2.5 at $1 per hour at 100 tokens per second, with a 50 tokens per second version at $0.30 per hour. Weights are available on Hugging Face, with inference support listed for SGLang, vLLM, Transformers, and KTransformers.

    Why it matters: The source gives benchmark scores against Claude and GPT models plus per-task token and runtime figures, so readers can weigh the cost-speed tradeoff directly.