Qwen3.8 27Bin opencode

Yes. Qwen3.8 27B Uncensored runs in opencode through this endpoint as qwen3.8-27b-uncensored, at $1.50 per million input tokens and $5.00 per million output tokens ($0.50 for cached input). The budget pick. A small, cheap uncensored Qwen with a million tokens of context and tool calling. The budget pick for agents.

Model id: qwen3.8-27b-uncensored
Build: Uncensored
Context: 1M tokens
Tools / reasoning / images: Yes / Yes / Yes
Per million tokens: $1.50 in / $5.00 out
Base model score: 34 on Artificial Analysis

Where it fits

A small uncensored Qwen for the cheap, high-volume part of agent work: renaming, formatting, writing tests from a clear spec, summarising a file before a bigger model reads it. opencode has a separate "small_model" setting for exactly these jobs, and this is the model to put there.

What to watch for

It is the weakest reasoner here. Do not hand it the plan for a large change; hand it the pieces once the plan exists.

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": {
        "qwen3.8-27b-uncensored": {
          "name": "Qwen3.8 27B Uncensored",
          "tool_call": true,
          "reasoning": true,
          "attachment": true,
          "limit": { "context": 1048576, "output": 32000 }
        }
      }
    }
  },
  "model": "uncensored-opencode/qwen3.8-27b-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/qwen3.8-27b-uncensored "Write unit tests for every exported function in src/utils"

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, MiMo V2.6 Flash, GLM 5.3 Flash Cyber.

Bring your agent.

Get an API key Set up opencode See the models