Xiaomi MiMo V2.6

MiMo V2.6 (xiaomi/mimo-v2.6-*) — a Xiaomi family of three tiers of the same model: flash — cheap everyday, pro — the workhorse, pro-ultraspeed — the maximum generation-speed tariff. Thinking is always on (the depth is not controllable); images are accepted, files — no.

Parameters and capabilities

Parameter	Value
model	xiaomi/mimo-v2.6-flash, xiaomi/mimo-v2.6-pro, xiaomi/mimo-v2.6-pro-ultraspeed
Reasoning	always on, reasoning_effort is not supported
Images on input	yes (image_url, data URLs)
Files on input	no — a file part returns 400

Tiers and prices

Model	Input/output per 1M	Profile
mimo-v2.6-flash	$0.17 / $0.35	bulk simple queries
mimo-v2.6-pro	$0.54 / $1.09	the everyday workhorse
mimo-v2.6-pro-ultraspeed	$5.438 / $10.875	priority generation speed

Example

curl https://api.mixen.ai/v1/chat/completions \
  -H "Authorization: Bearer $MIXEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.6-pro",
    "messages": [{"role": "user", "content": "Summarize this article: <text>"}]
  }'

Strengths and limitations

• The reasoning depth is not selectable — the model decides how much to think; reasoning tokens are always billed.
• Files are not accepted on input; images are.
• UltraSpeed pays for token delivery speed, not quality: quality matches Pro.

All models — in the catalog. The general workflow — chat guide.