跳到正文
Vercel Blog(vercel.com)· Zachary Chen·· 2026-09-21品質評分62

MiMo V2.6 模型現已在 AI Gateway 上可用

MiMo V2.6 models now available on AI Gateway

重點導讀

MiMo V2.6 Pro、Flash 與 Pro UltraSpeed 三款來自小米的模型現已在 AI Gateway 上可用。

它們支援文本、影像、音訊和影片輸入,並具備推理、工具呼叫、JSON 輸出、提示快取等功能,擁有 1M-token 上下文視窗和最高 128K 輸出 token。

AI 伴隨問答

自備 Key 深度分析

針對這篇報導有疑問?可直接點選快捷問題或向 AI 追問背景脈絡與技術細節:

正文

MiMo V2.6 Pro, MiMo V2.6 Flash, and MiMo V2.6 Pro UltraSpeed from Xiaomi are now available on AI Gateway.

All three models accept text, image, audio, and video inputs. They support reasoning, tool calling, JSON output, and prompt caching, with a 1M-token context window and up to 128K output tokens.

Choose a model based on your workload:

  • xiaomi/mimo-v2.6-pro is the flagship model for complex software engineering, long-running agent tasks, and professional workflows, with 1.02T total parameters and 42B active per token.

  • xiaomi/mimo-v2.6-flash is the more efficient, lower-cost option for coding, automation, and everyday agent workflows, with 309B total parameters and 15B active per token.

  • xiaomi/mimo-v2.6-pro-ultraspeed runs the same Pro model at up to 20 times the output speed for interactive agents and other latency-sensitive workflows.

To use MiMo V2.6:

Try MiMo V2.6 Pro, Flash, or Pro UltraSpeed in the model playground.

來源: Vercel Blog (vercel.com)
開啟原文

讀者討論

理性交流 · 即時討論