MiMo-V2.6-Pro-UltraSpeed: API pricing, context window and capabilities

Prices from official vendor price lists · October 2026

MiMo-V2.6-Pro-UltraSpeed costs $4.35 per 1M input tokens and $8.7 per 1M output tokens, with a 1M context window. Top of Xiaomi’s range and dearer than 80% of this rating.

Visit Xiaomi All Xiaomi models

Capabilities

API $/1M (in / out)

$4.35 / $8.7

Context window

1M tokens

Price / mo

API only

Overview Reviews

MiMo-V2.6-Pro-UltraSpeed is an AI model from Xiaomi, priced at $4.35 input and $8.7 output per 1M tokens. That places it in the frontier tier of this rating — dearer than 80% of the 205 priced models listed.

It holds 1M tokens in a single conversation, enough for a full codebase or a contract bundle in one pass. Capabilities recorded in this rating: text & chat, vision, audio, video, reasoning. Access is through the API rather than a consumer subscription.

API price$4.35 / $8.7per 1M tokens, in / out

Context1M tokenstokens per conversation

VendorXiaomiall models from this vendor

TierFrontierdearer than 80% of models

Cost calculator

1M tokens/mo10M tokens/mo50M tokens/mo200M tokens/mo

Standard$7.61~~AED 28 per month~~

With batch −50%$3.81~~AED 14 per month~~

With caching on input$6.63~~AED 24 per month~~

Standard$76.12~~AED 280 per month~~

With batch −50%$38.06~~AED 140 per month~~

With caching on input$66.34~~AED 244 per month~~

Standard$381~~AED 1,398 per month~~

With batch −50%$190~~AED 699 per month~~

With caching on input$332~~AED 1,218 per month~~

Standard$1,522~~AED 5,591 per month~~

With batch −50%$761~~AED 2,796 per month~~

With caching on input$1,327~~AED 4,872 per month~~

Assumes a 1:3 input-to-output ratio, which is typical for chat and generation. Dirham figures use 3.6725 per dollar. Batch and caching discounts apply where the vendor offers them.

Compared with alternatives

How MiMo-V2.6-Pro-UltraSpeed sits against its neighbours in this rating. Tap a card to open that model.

Mistral Medium 3.5

Cheaper

Mistral AI

$1.5 / $7.5256K tokens

Good and poor fit

Good fit

Multi-step analysis, planning and code review, where the first plausible answer is often wrong.
Reading screenshots, charts, scanned documents and photos.
Whole codebases, contract bundles and long transcripts in a single pass.

Poor fit

Classification, routing and short summaries — a small model does these identically for a fraction of the price.

Related filters

Text & chat234 models for text generation and chat

Vision159 models that read images

Reasoning175 models that think before answering

Tool calling172 models that call your functions

Long context 1M+88 models holding 1M tokens or more

Xiaomi5 models from this vendor

All 245 modelsThe full rating with filters and prices

Frequently asked questions

How much does MiMo-V2.6-Pro-UltraSpeed cost?

$4.35 / $8.7 per 1M tokens, input and output. In dirhams that is roughly AED 15.98 per 1M input tokens. Batch processing halves it where the vendor offers it.

What is the context window of MiMo-V2.6-Pro-UltraSpeed?

1M tokens in a single conversation.

What can MiMo-V2.6-Pro-UltraSpeed do?

In this rating it is recorded with: text & chat, vision, audio, video, reasoning, web search grounding, tool calling, structured JSON output, long context 1M+, prompt caching, multilingual, proprietary API.

Is MiMo-V2.6-Pro-UltraSpeed a good choice?

It depends on the job. See the good-fit and poor-fit lists above, and compare against the neighbouring models before committing.

Ratings 0

Avg. score 0

Rate this page

Help us improve