MiniMax Provider

MiniMax H3 Max is a video generation model jointly released by MiniMax and fal.ai, post-trained by fal.ai on MiniMax H3 and optimized for high-speed generation. It delivers mainstream 480P and 768P output and generates faster than MiniMax H3. It currently supports Text-to-Video and Image-to-Video, with Reference Generation coming soon.

Extremely fast generation at a low price, well suited for both image-to-video and text-to-video. It also performs quite well on simple r2va tasks, making it highly suitable for large-scale content generation scenarios.

MiniMax H3 is a lightweight, open-weights video generation model from MiniMax. It is designed for precise multimodal editing and controlled content generation, including instruction-guided edits, text and brand rendering, and video-to-video motion transfer.

The model is suited for commercial creative workflows across advertising, e-commerce, gaming, and interface design, with native audiovisual output for reference-driven generation.

Low cost, strong quality, and fast generation, with excellent reference-to-video performance. Ideal for scenarios that require a balanced combination of output quality, capability, and speed.

H3-Fast is an ultra-fast video generation model built on post-training optimization of the MiniMax H3 standard version. It outputs 480P and 768P videos up to 15 seconds long, and supports text-to-video, image-to-video, and multimodal reference-based video generation. It is optimized for faster, lower-cost batch video creation across e-commerce, advertising, and marketing workflows.

MiniMax-M3.1-Flash is a frontier multimodal language model with a 1M-token context window, designed for agentic reasoning, tool use, coding, and long-context tasks. It supports text, image, and video inputs, and offers tunable thinking depth through effort levels to balance reasoning quality, latency, and token usage.

MiniMax M3 is the first open-weights flagship that brings coding, agentic reasoning, million-token context, and native multimodality together in one model. It handles autonomous task decomposition, tool use, and multi-step reasoning with ease — and writes code that's meant to ship, not code that just runs. Built on MiniMax's proprietary Sparse Attention architecture, M3 natively supports million-token context windows for long-horizon agents, large codebases, and long-video understanding. Its multimodality isn't bolted on — it's trained in from day one, with text and vision deeply aligned at the semantic level.

M2-her text chat model, designed for role-playing, multi-turn conversations and dialogue scenarios.

MiniMax-M2.1 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.

Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.

To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns.

M2.7 delivers outstanding performance in real-world software engineering, including end-to-end complete project delivery, log analysis and bug triaging, code security, machine learning, and more. On the benchmark SWE-Pro, M2.7 scores 56.22%, nearly matching the level of Opus. This capability also extends to end-to-end complete project delivery scenarios (VIBE-Pro 55.6%) and deep understanding of complex engineering systems on Terminal Bench 2 (57.0%).

In the professional office domain, we have improved the model's specialized knowledge and task delivery capabilities across various fields. On GDPval-AA, its ELO score is 1495, the highest among open-source models. M2.7's ability to perform complex editing in the Office suite (Excel/PPT/Word) has significantly improved, enabling better multi-round revisions and high-fidelity editing. M2.7 is capable of interacting with complex environments. Across 40 complex skills (> 2000 tokens) cases, M2.7 still maintains a 97% skill adherence rate. In OpenClaw usage, M2.7 has shown significant improvement compared to M2.5, scoring close to the latest Sonnet 4.6 in the MMClaw evaluation.

M2.7 possesses excellent identity retention capabilities and emotional intelligence. Beyond productivity use cases, it also opens up space for innovation in interactive entertainment scenarios.

M2.7 highspeed: Same performance, faster, more agile

MiniMax-M2 is a compact, high-efficiency large language model optimized for end-to-end coding and agentic workflows. With 10 billion activated parameters (230 billion total), it delivers near-frontier intelligence across general reasoning, tool use, and multi-step task execution while maintaining low latency and deployment efficiency. The model excels in code generation, multi-file editing, compile-run-fix loops, and test-validated repair, showing strong results on SWE-Bench Verified, Multi-SWE-Bench, and Terminal-Bench. It also performs competitively in agentic evaluations such as BrowseComp and GAIA, effectively handling long-horizon planning, retrieval, and recovery from execution errors. Benchmarked by Artificial Analysis, MiniMax-M2 ranks among the top open-source models for composite intelligence, spanning mathematics, science, and instruction-following. Its small activation footprint enables fast inference, high concurrency, and improved unit economics, making it well-suited for large-scale agents, developer assistants, and reasoning-driven applications that require responsiveness and cost efficiency.

MiniMax-M2.5 is a lightweight, state-of-the-art large language model optimized for coding, agentic workflows, and modern application development. With only 10 billion activated parameters, it delivers a major jump in real-world capability while maintaining exceptional latency, scalability, and cost efficiency.

Compared to its predecessor, M2.1 delivers cleaner, more concise outputs and faster perceived response times. It shows leading multilingual coding performance across major systems and application languages, achieving 49.4% on Multi-SWE-Bench and 72.5% on SWE-Bench Multilingual, and serves as a versatile agent “brain” for IDEs, coding tools, and general-purpose assistance.

To avoid degrading this model's performance, MiniMax highly recommends preserving reasoning between turns.

M2.5 highspeed: Same performance, faster, more agile