Skip to main content
AI Choice Engine

Xiaomi

Xiaomi MiMo-V2.6-Pro

Xiaomi MiMo-V2.6-Pro is a Xiaomi model with 1.05M context, $0.435 in / $0.87 out per million tokens, last verified October 25, 2026. Open weights: yes. Public-board scores are linked to the publisher; vendor-only figures stay in the watch-out, not on the board.

MiMo-V2.6-Pro is Xiaomi's open-weight MIT 1.02T MoE with text, image, video and audio input and a 1M context.

Recorded profile verification October 25, 2026Individual provider fields may change

AI model specification details
SpecificationXiaomi MiMo-V2.6-Pro
ProviderXiaomi
TierFrontier
Context window1.05M
Max output131K
Input / 1M tokens$0.435
Output / 1M tokens$0.87
WeightsOpen
Parameters1.02T total / 42B active (MoE)
Reasoning levelsNot verifiedUnverified
Modalitiestext, image, video, audio
LicenseMIT
API model idmimo-v2.6-pro
ReleasedSeptember 22, 2026

Pricing tiers: Xiaomi overseas realtime USD/MTok input/output $0.435/$0.87, cached input $0.0036; Batch $0.2175/$0.435, cached $0.0018. Domestic RMB/MTok realtime input/output ¥3/¥6, cache ¥0.025; Batch ¥1.50/¥3, cache ¥0.0125. Cache writes are limited-time free without an end date. Overseas search is $5/1,000 calls; domestic search ¥16/1,000. Token Plan quota and PAYG balance are separate. Distinct Pro-Ultraspeed realtime USD $4.35/$8.70, cache $0.036; domestic ¥30/¥60, cache ¥0.25; no Batch support. Throughput up to 20x is a vendor claim, not a measured task-speed multiplier.

Publisher evidence

Published benchmark results

Each result keeps its source date visible. Dates refer to source publication or capture unless the source explicitly states when it measured the result. A missing benchmark is not treated as a zero.

Published benchmark results for Xiaomi MiMo-V2.6-Pro
BenchmarkScoreSource dateSource
Artificial Analysis Intelligence IndexMiMo-V2.6-Pro462026-10-01Artificial Analysis · View source
DeepSWE 1.1Xiaomi publisher table; common run settings and experiment date unverifiedCross-model comparability not verified71.9%2026-10-02Xiaomi MiMo-V2.6 announcement (vendor-reported; October 2 source capture, not an experiment date) · View source
Terminal-Bench 2.1Xiaomi publisher table; common run settings and experiment date unverifiedCross-model comparability not verified89.9%2026-10-02Xiaomi MiMo-V2.6 announcement (vendor-reported; October 2 source capture, not an experiment date) · View source

Best for

  • Open-weight frontier work
  • Omni-modal input
  • Cheap long-context API

Watch out

Thinking defaults enabled via thinking.type=enabled/disabled; no graded effort enum is documented. The 131,072 completion budget includes reasoning and final output. Thinking forces temperature=1.0/top_p=0.95. Complete reasoning_content must pass through subsequent tool-call turns or the API can return 400. Native checkpoint context is 1,048,576; hosted docs advertise 1M. Limits are per account/model, not per API key. MIT weights disclose 1.02T total/42B active parameters. The old V2.5-Pro alias was temporarily routed to this endpoint before expiry; its historical benchmark observations remain attached to V2.5-Pro, not to this replacement.

History

Xiaomi MiMo-V2.6-Pro timeline

Release and status events for this model that passed two-source verification — dated, sourced, and linked.

  • Xiaomi MiMo-V2.6-Pro + V2.6-FlashReleaseSeptember 22, 2026

    Xiaomi releases MiMo-V2.6-Pro (1.02T/42B MoE, 1M context, MIT weights) and V2.6-Flash with omni-modal input at unchanged API prices ($0.435/$0.87 and $0.14/$0.28 per MTok).

    Xiaomi dated model release log

Common questions

Xiaomi MiMo-V2.6-Pro

Answered from the verified figures on this page rather than general guidance.

How much does Xiaomi MiMo-V2.6-Pro cost per million tokens?
Xiaomi MiMo-V2.6-Pro lists base rates of $0.435 per million input tokens and $0.87 per million output tokens. Estimate both input and output token volume and any additional charges for your workload. Xiaomi overseas realtime USD/MTok input/output $0.435/$0.87, cached input $0.0036; Batch $0.2175/$0.435, cached $0.0018. Domestic RMB/MTok realtime input/output ¥3/¥6, cache ¥0.025; Batch ¥1.50/¥3, cache ¥0.0125. Cache writes are limited-time free without an end date. Overseas search is $5/1,000 calls; domestic search ¥16/1,000. Token Plan quota and PAYG balance are separate. Distinct Pro-Ultraspeed realtime USD $4.35/$8.70, cache $0.036; domestic ¥30/¥60, cache ¥0.25; no Batch support. Throughput up to 20x is a vendor claim, not a measured task-speed multiplier.
What is Xiaomi MiMo-V2.6-Pro's context window?
Xiaomi MiMo-V2.6-Pro accepts about 1.05M tokens of context. That only matters if you routinely send very long documents, large codebases, or multi-turn histories that approach that limit.
What is Xiaomi MiMo-V2.6-Pro best for?
Xiaomi MiMo-V2.6-Pro is a frontier tier from Xiaomi. It suits open-weight frontier work, omni-modal input, cheap long-context api. Thinking defaults enabled via thinking.type=enabled/disabled; no graded effort enum is documented. The 131,072 completion budget includes reasoning and final output. Thinking forces temperature=1.0/top_p=0.95. Complete reasoning_content must pass through subsequent tool-call turns or the API can return 400. Native checkpoint context is 1,048,576; hosted docs advertise 1M. Limits are per account/model, not per API key. MIT weights disclose 1.02T total/42B active parameters. The old V2.5-Pro alias was temporarily routed to this endpoint before expiry; its historical benchmark observations remain attached to V2.5-Pro, not to this replacement.
Can I self-host Xiaomi MiMo-V2.6-Pro?
Xiaomi MiMo-V2.6-Pro publishes open weights, but self-hosting depends on the licence, hardware footprint, quantisation quality, and serving stack. A hosted API is often cheaper until you have measured throughput and concurrency on your own hardware.