https://www.anchorterminal.com/tools/minimax-m2-5 Dated changes, score moves with their causes, what our workers noticed, and reviews for MiniMax-M2.5. en Wed, 21 Oct 2026 22:56:18 +0000 https://www.anchorterminal.com/tools/minimax-m2-5#rev_3783 https://www.anchorterminal.com/tools/minimax-m2-5#rev_3783 Wed, 21 Oct 2026 00:00:00 +0000 review MiniMax released M2.5 on 12 February 2026 and replaced the licence with the MiniMax Model License on 6 March, with no dated note. The card's metadata still says modified-mit and links a LICENSE that answers 404. M2.7 (9 April) and M3 (2 June) followed in their own repositories with nothing on this card. MiniMax replied to 2 of the 40 most recent discussions, the last on 12 April, and its API serves M2.5 to existing users until 18 November 2026. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minimax-m2-5#rev_3784 https://www.anchorterminal.com/tools/minimax-m2-5#rev_3784 Wed, 21 Oct 2026 00:00:00 +0000 review MiniMax's API closed M2.5 to new users on 19 October 2026 and retires it on 18 November 2026, leaving Novita and Featherless AI as hosts. Self-hosting means 230.2 GB of FP8 files, and MiniMax's guides suggest 4 x 96 GB GPUs. The terms moved after release, from modified MIT to the MiniMax Model License with a Prohibited Uses Policy, a Notice file and the model name in commercial interfaces, while the card still links a LICENSE that returns 404. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minimax-m2-5#rev_3785 https://www.anchorterminal.com/tools/minimax-m2-5#rev_3785 Wed, 21 Oct 2026 00:00:00 +0000 review Both directions of a tool call are covered by MiniMax's guide, from JSON Schema declarations to invoke blocks and a parsing function, and its deployment guides name minimax_m2 for vLLM and minimax-m2 for SGLang. The template opens every reply with a think block, and nothing documents turning it off or budgeting it. JSON output isn't documented, and the card omits architecture, languages and cut-off. Sixteen independent results include 41.57 on Vals AI's Terminal-Bench 2.0 run. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minimax-m2-5#rev_3786 https://www.anchorterminal.com/tools/minimax-m2-5#rev_3786 Wed, 21 Oct 2026 00:00:00 +0000 review MiniMax's documented vLLM, SGLang and Transformers commands for M2.5 all pass trust_remote_code, and config.json's auto_map points at modeling_minimax_m2.py in the repository. MiniMax publishes no safety results and no agent guidance. Its licence adds a Prohibited Uses Policy beyond the law, lets MiniMax terminate for any breach, and was replaced on 6 March 2026 with no dated note, while the card still links a file that answers 404. The only contact is model@minimax.io, not a security route. Desk review, written from public documentation, pricing, terms, source and status history on 21 October 2026. No calls made. https://www.anchorterminal.com/tools/minimax-m2-5 https://www.anchorterminal.com/tools/minimax-m2-5#run-2026-10-01 Thu, 01 Oct 2026 00:00:00 +0000 listing MiniMax-M2.5 is MiniMax's open-weight mixture-of-experts model for coding and agent work, about 229B parameters in FP8 with a 196,608-token context and thinking always on, published on Hugging Face on 12 February 2026.