MiMo V2.6 Flashin opencode

Yes. MiMo V2.6 Flash Uncensored runs in opencode through this endpoint as mimo-v2.6-flash-uncensored, at $1.00 per million input tokens and $2.00 per million output tokens ($0.50 for cached input). Abliterated MiMo with vision. Xiaomi MiMo with the refusal direction removed. A million tokens of context, tool calling and vision.

Model id: mimo-v2.6-flash-uncensored
Build: Abliterated
Context: 1M tokens
Tools / reasoning / images: Yes / Yes / Yes
Per million tokens: $1.00 in / $2.00 out
Base model score: 38 on Artificial Analysis

Where it fits

Xiaomi MiMo with the refusal direction removed from its weights, which is abliteration in the strict sense. It reads images, so it works for front-end sessions where you paste what the page looks like and ask for the fix.

What to watch for

It scores a little under the GLM and DeepSeek Flash models on general benchmarks, so keep it for the tasks where its refusal-free behaviour or its vision is the reason you chose it.

The config

opencode.json

{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "uncensored-opencode": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Uncensored Opencode",
      "options": {
        "baseURL": "https://uncensoredopencode.com/v1",
        "apiKey": "{env:UNCENSORED_OPENCODE_API_KEY}"
      },
      "models": {
        "mimo-v2.6-flash-uncensored": {
          "name": "MiMo V2.6 Flash Uncensored",
          "tool_call": true,
          "reasoning": true,
          "attachment": true,
          "limit": { "context": 1048576, "output": 32000 }
        }
      }
    }
  },
  "model": "uncensored-opencode/mimo-v2.6-flash-uncensored"
}

Your key goes in UNCENSORED_OPENCODE_API_KEY. The opencode page has the setup steps and the block with every model in it.

A first task for it

shell

opencode run --model uncensored-opencode/mimo-v2.6-flash-uncensored "Here is a screenshot of the broken layout. Find the CSS that causes it and fix it"

The score above is the base model's, from the Artificial Analysis Intelligence Index v4.3.2. We do not claim this build scores the same.

Next to it on the line: GLM 5.3 Flash, Kimi K3.1 Pro, GLM 5.3, DeepSeek V4.1 Flash 1017, Qwen3.8 27B, GLM 5.3 Flash Cyber.

Bring your agent.

Get an API key Set up opencode See the models