Velqons
MODELS / XIAOMI

MiMo V2.6 Flash

MiMo-V2.6-Flash is an open-source Mixture-of-Experts model from Xiaomi with 309B total parameters and 15B activated per token. Its hybrid attention (sliding-window layers interleaved with global attention) keeps long-context serving efficient across a 1M-token context window.…

TEXTREASONINGAUDIO-INPUTIMPLICIT-CACHINGREASONINGSTRUCTURED-OUTPUTTOOL-USEVIDEO-INPUTVISION
1.0M
CONTEXT WINDOW
131.1K
MAX OUTPUT TOKENS
$0.04
INPUT PRICE / 1M TOKENS
$1.28
OUTPUT PRICE / 1M TOKENS
QUICKSTART

Call it in one request.

OpenAI-compatible: change the base URL, and the setup is complete.

curl https://enterprise.velqons.com/v1/chat/completions \
  -H "Authorization: Bearer $VELQONS_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "blackboxai/xiaomi/mimo-v2.6-flash",
    "messages": [{ "role": "user", "content": "Hello!" }],
    "stream": true
  }'
SPECIFICATIONS

The full spec sheet.

Context, pricing, modalities, routing, and deployment: everything MiMo V2.6 Flash supports, in one table.

MODEL ID
blackboxai/xiaomi/mimo-v2.6-flash
DEVELOPED BY
Xiaomi
MODEL TYPE
Text
RELEASED
Sep 21, 2026
CONTEXT WINDOW
1.0M
MAX OUTPUT TOKENS
131.1K
INPUT MODALITIES
text, audio, image, video
OUTPUT MODALITIES
text
INPUT PRICE
$0.04 / 1M tokens
OUTPUT PRICE
$1.28 / 1M tokens
CACHE READ
$0.04 / 1M tokens
REASONING
Supported
DATA RETENTION
Standard retention
DEDICATED DEPLOYMENT
Enterprise · single-tenant
SUPPORTED PARAMETERS
max_tokenstemperaturestoptoolstool_choicereasoninginclude_reasoningresponse_formatstructured_outputs