Vercel has added Xiaomi's MiMo V2.6 Pro, Flash and Pro UltraSpeed to AI Gateway. Developers can select these models through the gateway's common API, which also manages usage tracking and routing. This supplies a hosted access path for applications and coding agents.
The release positions Pro for complex software work and Flash as the more efficient option for everyday automation. Pro UltraSpeed serves the Pro model with a claimed output-speed increase of up to twentyfold. That describes how quickly output is produced; choosing among the variants still depends on the application's workload. The announcement's concrete change is access to these options through one existing integration.
Key takeaways · AI-distilled
MiMo V2.6 Pro is a sparse mixture-of-expertsA model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.Full definition → model with 1.02T total parameters but only 42B activated per token, aimed at complex software-engineering and long-running AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition → work.
MiMo V2.6 Flash uses a much smaller MoE, 309B total parameters with 15B activated per token, positioned as the efficient tier for everyday multimodalA model that works with more than text — reading images, audio, or video, and sometimes generating them too.Full definition → automation rather than heavy coding work.
Beyond its 1M-token input context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition →, the MiMo V2.6 family supports up to 128K output tokens per response on AI Gateway.
Terms in this piece · Glossary
multimodal — A model that works with more than text — reading images, audio, or video, and sometimes generating them too.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
mixture-of-experts — A model built from many specialist sub-networks where only a few activate per token, giving big-model capability at small-model running cost.
