← Choose models

Language & coding

What mattersMiMo V2.6 Pro ↗Xiaomi
Use casesReasoning · Agents & tools · Coding · Documents & writing · Visual understanding
Model score38Conservative editorial adjustmentArtificial Analysis · MiMo V2.6 Pro · reasoning ↗
Output / 1M tokens · USD$0.435
Published rates · USD$0.435 input / $0.87 outputPer 1M native tokens
Cached input / 1M$0.0036
Cache write / 1M$0
Pricing conditionsXiaomi MiMo API · overseas USD · real-timePublished USD rates, not a conversion of domestic CNY prices. Cache writes are temporarily free. Batch pricing and Token Plan subscriptions are separate; web search is billed additionally.Xiaomi MiMo API pricing ↗
Output speed · tokens/s42.8 tokens/sXiaomi API · MiMo V2.6 Pro · reasoning model. Artificial Analysis reports a rolling 72-hour median of output speed after the first token, not total response time. Checked 2026-10-05; speed varies with workload and serving conditions.Artificial Analysis · MiMo V2.6 Pro ↗Artificial Analysis · performance methodology v2.2.0 ↗ · Checked 2026-10-05
Context window1,000,000
Model IDmimo-v2.6-pro
Version notesAccepts text, image, video, and audio input; generates text. Video understanding is not video generation. This entry covers regular Pro, not the separately priced Pro UltraSpeed endpoint. Its price and speed must not be mixed with that serving tier.
Official documentationXiaomi · MiMo V2.6 Pro ↗Checked 2026-10-05
Language prices are USD per million tokens; input and output are billed separately. Video samples use 5s of 768P output where verified. Extra tools, reasoning, cache writes, input media, storage, and taxes can change the total. (fast) marks a published median output speed above 150 tokens/s in the linked test settings.