# MiniMax M2.5

MiniMax M2.5 é um modelo de MiniMax com pesos abertos, lançado em 2026-02. A janela de contexto é de 204.800 tokens.

- Desenvolvedor: MiniMax
- Id: minimaxai/minimax-m2.5
- Segundo relatos: 2026-11-11T21:57:04.000Z
- Detecção: 2026-10-07T19:40:22.731Z
  - [link de referência](https://huggingface.co/MiniMaxAI/MiniMax-M2.5)
- Status: Lançado
- Versão dos pesos: 2026-02-12
  - [link de referência](https://huggingface.co/api/models/MiniMaxAI/MiniMax-M2.5/paths-info/2515a3ea0afec1dd22d0c7794b3a91557804d195)
- Canônico: https://alexgetman.com/pt/models/minimax/minimax-m2-5-725/

## Perguntas

### Qual é a janela de contexto do MiniMax M2.5?

A janela de contexto é de 204.800 tokens.

### O MiniMax M2.5 tem pesos abertos?

Sim. MiniMax disponibiliza os pesos.

### Quando o MiniMax M2.5 foi lançado?

Em 2026-02.

## Cronologia

- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · AMD-AGI/AKLR · @zhenhuang12](https://github.com/AMD-AGI/AKLR/pull/194)
> glm-5.3 53, deepseek-v4-flash 45, deepseek-r1 40, deepseek-v3 40, minimax-m2.5 32, muse-spark 11, minimax-m3.1 5. 17 scenarios name two models.
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · inference-sim/accuracy-dashboard · @sriumcp](https://github.com/inference-sim/accuracy-dashboard/pull/72)
> catalog model name, and the NVFP4 points use `minimax-m2.5-nvfp4` while the entries say `minimax-m2.5`. Should the reader match on the model family, or should the
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · inference-sim/blis-vllm · @sriumcp](https://github.com/inference-sim/blis-vllm/pull/115)
> and 289 us over NVLink for 8192 tokens (MiniMax-M2.5, ib-400g), and the assumption is disclosed either way. Fails if the rack is always the hardware's
- 2026-11-13T19:04:38.386Z · [GitHub search · MiniMax · pulls · lostcoords/yuke · @yuke-catalog-action[bot]](https://github.com/lostcoords/yuke/pull/8)
- 2026-11-13T19:05:09.193Z · [GitHub search · MiniMax · commits · ThinkInAIXYZ/PublicProviderConf · @zerob13](https://github.com/ThinkInAIXYZ/PublicProviderConf/commit/4502daa261a763324ec48102d7d3505bf58a87e2)
> updated: Qwen3.5 9B, Gemma 4 26B A4B IT, MiniMax-M2.5 - LLM Gateway: +7 models, 8 updates

## Links de referência

- [GitHub search · MiniMax · pulls · AMD-AGI/AKLR · @zhenhuang12](https://github.com/AMD-AGI/AKLR/pull/194)
- [GitHub search · MiniMax · commits · ThinkInAIXYZ/PublicProviderConf · @zerob13](https://github.com/ThinkInAIXYZ/PublicProviderConf/commit/4502daa261a763324ec48102d7d3505bf58a87e2)
- [GitHub search · MiniMax · pulls · inference-sim/accuracy-dashboard · @sriumcp](https://github.com/inference-sim/accuracy-dashboard/pull/72)
- [GitHub search · MiniMax · pulls · inference-sim/blis-vllm · @sriumcp](https://github.com/inference-sim/blis-vllm/pull/115)
- [GitHub search · MiniMax · pulls · lostcoords/yuke · @yuke-catalog-action[bot]](https://github.com/lostcoords/yuke/pull/8)
- [huggingface-router](https://huggingface.co/MiniMaxAI/MiniMax-M2.5)
- [hf-author-artifacts:MiniMaxAI](https://huggingface.co/api/models/MiniMaxAI/MiniMax-M2.5/paths-info/2515a3ea0afec1dd22d0c7794b3a91557804d195)

## Sinais