xiaomi · Open weights

MiMo V2.6 Flash Uncensored

Added Sep 25, 2026Open weights

A lower-refusal MiMo V2.6 Flash finetune with a 1M-token context window, separate reasoning output, and tool calling. Supports image input and adjustable thinking effort.

Reasoning
Tools
Vision

Input: Text, Images
Output: Text
Reasoning effort: none · low · medium · high
Discovery tier: Open weights

Pricing

USD per 1M tokens

Input: $0.50
Output: $1.50
Cache read: $0.20

Reference prices as published by the model provider. API example

Specifications

Context window: 1M
Max output: 65.5K
Average output (7 days): 1.2K tokens; Longer than 76% of 465 models

Side by side

MiMo V2.6 Flash Uncensored compared

Specifications, prices, speed and benchmark scores next to each other. Benchmarks below show every compared model too.

Limits
	MiMo V2.6 Flash UncensoredxiaomiThis model	MiMo V2.6 Flash AbliteratedxiaomiRemove
Provider	xiaomi	xiaomi
Discovery tier	Open weights	Open weights
Added	Sep 25, 2026	Sep 25, 2026
Context window	1.05M	1.05M
Max output	65.54K	65.54K
Average output	1.2K tokens	1.3K tokens
Pricing, USD per 1M tokens
Input	$0.50	$0.50
Output	$1.50	$1.50
Cache read	$0.20Best	$0.28
Performance
Throughput	159.2 tok/sBest	130.9 tok/s
Time to first token	1.3 sBest	2.4 s
Request success (24h)	98.6%Best	98.4%
Capabilities
Reasoning	Yes	Yes
Tools	Yes	Yes
Vision	Yes	Yes
Reasoning effort	none, low, medium, high	none, high

Public evaluations

Benchmarks

There are no public benchmark results for these models yet.

Live routing data

Performance and reliability

Recent averages across requests routed for this model. Your own speed depends on prompt length, reasoning effort and load.

Throughput: 159.2 tok/s; Faster than 77% of 250 models
Time to first token: 1.3 s; Quicker than 90% of 250 models
Prompt cache hits: 86.5%; About $0.24 per 1M input tokens with caching
Request success (24h): 98.6%; Reliable

Cache hits are the share of input tokens recently served from a prompt cache across all requests. They are not a forecast of your own hit rate.

Hourly request success · last 72 hoursLowest hour 0.0%

Healthy (98% or more)
Degraded (90–98%)
Down (under 90%)
No requests

Developers

Use it through the API

Noumen’s API is OpenAI-compatible: any Chat Completions client works with a base URL and a key.

Read the quickstart

curl https://www.noumen.xyz/api/v1/chat/completions \
  -H "Authorization: Bearer $NOUMEN_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "xiaomi/mimo-v2.6-flash-uncensored",
    "reasoning_effort": "medium",
    "messages": [{ "role": "user", "content": "Explain this stack trace." }]
  }'

import os
from openai import OpenAI

client = OpenAI(base_url="https://www.noumen.xyz/api/v1", api_key=os.environ["NOUMEN_API_KEY"])
reply = client.chat.completions.create(
    model="xiaomi/mimo-v2.6-flash-uncensored",
    messages=[{"role": "user", "content": "Explain this stack trace."}],
)
print(reply.choices[0].message.content)

xiaomi

Other xiaomi models, starting with the same family.