Xiaomi MiMo-v2.5 Series API Permanent Price Reduction Up to 99%

Source: Hacker News

MiMo-V2.5 Series Price Adjustment Announcement | 100 Trillion Token Creator Incentive Plan Concludes

Effective Time: 0:00, May 27 2026, Beijing Time

Quick Overview of the Core of This Announcement

• MiMo-V2.5 Series API Permanent Price Reduction
• TokenPlan billing system optimization, with usage increased to 5–8 times the original
• The Creator Incentive Program for Quadrillion Tokens Concludes Successfully
• Full reset of the current effective TokenPlan user quota

MiMo-V2.5 Series API Permanent Price Reduction

Compared to the original API pricing, the new pricing can have a maximum reduction of up to 99 %, and no longer differentiates based on the input length.

This price adjustment officially takes effect at 0:00 on May 27th, Beijing time, with global synchronization. We sincerely invite all developers to integrate and experience it.

Optimization of TokenPlan Billing System

• Increase the quantity without increasing the price – usage volume increased to 5–8 times the original, unlocking more abundant productivity.
• Billing rules have been adjusted to be clearer, more understandable, and “what you see is what you get.”

The Creator Incentive Program for Quadrillion Tokens Concluded Successfully

Since its launch on April 28, the “Trillion Token Creator Incentive Program” has been enthusiastically pursued and widely followed by users worldwide. As of 16:08 on May 26, Beijing Time, all 100 T Tokens have been fully distributed ahead of schedule, and the event has concluded successfully.

Note: The exclusive welfare activities for members of the Apache Software Foundation remain valid long‑term and are not affected by this finalization.

Surprise: All Existing TokenPlan User Quotas Have Been Fully Reset

Regardless of the current usage of the package, the Credits quota of all users who have subscribed to the Token Plan and are still within the validity period (including participants of the Quadrillion Token Creator Incentive Program and users with exclusive Apache Software Foundation benefits) will be fully reset at 0:00 on May 27th, Beijing Time, and implemented according to the new billing rules.

One More Thing: For historical paid users whose Token Plan has expired, we have prepared surprise gifts, which will be announced within the next week. Please stay tuned.

Optimization Instructions for Inference Technology

Behind this price adjustment is the continuous optimization of the inference system by Xiaomi’s technical team.

• We fully support SWA (Sliding Window Attention) based on SGLang HiCache, reducing the data transfer volume of KV Cache among multi‑level storage (GPU memory, CPU memory, SSD) to nearly 1/7 of the pre‑optimization level, and increasing the number of cacheable tokens to nearly 5 times the previous amount, significantly improving cache hit rate and inference efficiency.
• We further enhanced the input throughput capacity of the cluster by optimizing the expert parallelism scheme, input‑length bucketing strategy, etc., thereby continuously reducing the service cost per token while ensuring service quality.

Conclusion

The value of technology ultimately lies in the breadth of its use. Relying on continuous technological innovation, we hope to leverage real, sustainable, and large‑scale inference demand by providing model services that combine low cost with top‑notch capabilities, thereby promoting the construction of a complete AI infrastructure chain.

Enabling more people to use better models – this is MiMo’s unwavering mission.