Clef · Try the live demo →
Catalog
XiaomiHeabsy · EEA

MiMo V2.6 Flash Uncensored

MiMo V2.6 Flash Uncensored carries dealignai's weight-level refusal removal over to the MOPD weights of Xiaomi's MiMo V2.6 Flash. Vision input, separate reasoning and tool calling are kept, with a context of up to a million tokens. It complies with requests the original declines: it is meant for research and red-teaming, and anything shown to end users needs your own moderation layer. We serve it on hardware we operate inside the EEA; prompts and completions are not stored.

model id: mimo-v26-flash-unc

from openai import OpenAI client = OpenAI(    api_key="hb-...",    base_url="https://api.heabsy.com/v1",) r = client.chat.completions.create(    model="mimo-v26-flash-unc",    messages=[{"role": "user", "content": "Hello"}],)print(r.choices[0].message.content)

Use it in Claude Code · OpenCode · Cline · Kilo Code · SillyTavern · n8n

Context
1M tokens
Serving
Heabsy hardware · EEA
Tool calling
Reasoning
Structured output
Vision
Input
$0.4404/ 1M
Cached input
$0.1404/ 1M
Output
$1.4285/ 1M

Price list, updated 21 October 2026. No minimum spend, no subscription.

Which MiMo V2.6 is this?

MiMo V2.6 Flash runs on our own hardware in three variants: the official Xiaomi weights, Uncensored (dealignai's refusal removal carried into the weights) and Abliterated (refusal direction ablated with the Heretic method, applied as an adapter). The two uncensored variants are for research and red-teaming and need your own moderation in front of end users.

MiMo V2.6 Pro is a separate model of the same generation and is served by a partner provider, without zero data retention.

Technical details

Context window
1M tokens
Max output
65,536 tokens
Throughput limit
2M tok/min
Tokenizer
Other
Streaming
yes
Open weights
dealignai/MiMo-V2.6-Flash-RL-UNCENSORED
Supported parameters
max_tokens
1 … 65536
temperature
0 … 2
top_p
0 … 1
frequency_penalty
-2 … 2
presence_penalty
-2 … 2
stop
array
seed
integer
Computed in the EEA, never logged

This model runs on GPUs we operate inside the European Economic Area. Prompts and completions are not written to our logs or durable storage, nothing is used for training, and request content is processed in the EEA. How we serve our own models is described on the inference page.

Questions about this model

›Where is MiMo V2.6 Flash Uncensored computed?

Inside the European Economic Area, on hardware we operate. The catalog reports the processing region per model, so you can answer a supervisory authority without asking us.

›Does MiMo V2.6 Flash Uncensored store prompts and completions?

No. This model runs with zero data retention: request content is not written to durable storage and nothing is used for training.

›How large is the MiMo V2.6 Flash Uncensored context window?

1M tokens, with up to 65,536 tokens of output.

›What does MiMo V2.6 Flash Uncensored cost?

$0.4404 per million input tokens and $1.4285 per million output tokens. No minimum spend and no subscription; the same price list covers the API and the invoice.

›Is there a throughput limit on MiMo V2.6 Flash Uncensored?

Yes, 2M tokens per minute. Higher limits are a question of volume, not of principle.

Compare with similar models

ModelDeveloperParametersContextLicenceInput / 1M
MiMo V2.6 Flash UncensoredXiaomi—1M—$0.4404
MiMo V2.6 FlashXiaomi—1M—$0.4762
MiMo V2.6 Flash AbliteratedXiaomi—1M—$0.4762
MiMo V2.6 ProXiaomi—1M—$0.87

35 more models behind the same key and the same invoice.

Browse the catalog