MiMo V2.6 Flash — Uncensored

MiMo V2.6 Flash Uncensored for chat, coding and tool workflows. A published 1M-token context window and separate cached-input pricing.

Input / 1M tokens$0.6936

Cached input$0.17688

Output / 1M tokens$2.24985

Context length1,048,576

StatusAvailable

Model informationOpen chat API Playground Docs

Model and API details

Model version: MiMo V2.6 Flash — UncensoredVersion name published by the hosting service.
Hosting: Third-party inference service
Refusal reduction: The hosting service identifies this as an uncensored version tuned to reduce refusals.
API interface: Chat Completions · SSEUse the Chat Completions examples below. Tool calls, image input and other OpenAI endpoints need separate compatibility checks.
Context length: 1,048,576 tokensLimit published by the hosting service.
Maximum output tokens: 65,536 tokensInput and output share the context window. The free reply trial has its own smaller limits.

Compare answers on your own tasks before choosing. These are configured or provider-published specifications; independent quality and maximum-context results have not yet been published.

Information reviewed: 28 October 2026.

A familiar interface

Use an OpenAI-compatible client with your API key. Select a model ID from the live model directory.

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://uncensoredai.click/v1",
  apiKey: process.env.UNCENSOREDAI_API_KEY,
});

const response = await client.chat.completions.create({
  model: "MiMo_V2.6_Flash_Uncensored",
  messages: [{ role: "user", content: "Hello!" }],
});