Kimi K3.1 Proin opencode

Yes. Kimi K3.1 Pro Uncensored runs in opencode through this endpoint as kimi-k3.1-pro-uncensored, at $7.50 per million input tokens and $37.50 per million output tokens ($0.80 for cached input). The strongest model on the line. Kimi K3.1 Pro, uncensored: the strongest model on the line, with a million tokens of context, tool calling, reasoning and vision.

Model id: kimi-k3.1-pro-uncensored
Build: Abliterated
Context: 1M tokens
Tools / reasoning / images: Yes / Yes / Yes
Per million tokens: $7.50 in / $37.50 out
Base model score: 55 on Artificial Analysis

Where it fits

Use it for the work the smaller models get wrong: a refactor that crosses many files, a bug that needs the whole call chain held in mind, a plan that has to be right before any file is touched. It is an abliterated build, so it takes the security, scraping and reverse-engineering tasks a stock model stops on.

What to watch for

It costs the most per token here. A common split is Kimi for the plan and a Flash model for the edits, and you can switch between them inside a session with /models.

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": {
        "kimi-k3.1-pro-uncensored": {
          "name": "Kimi K3.1 Pro Uncensored",
          "tool_call": true,
          "reasoning": true,
          "attachment": true,
          "limit": { "context": 1048576, "output": 32000 }
        }
      }
    }
  },
  "model": "uncensored-opencode/kimi-k3.1-pro-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/kimi-k3.1-pro-uncensored "Plan how to split this module into three packages. List every file that moves before touching anything"

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, GLM 5.3, DeepSeek V4.1 Flash 1017, MiMo V2.6 Flash, Qwen3.8 27B, GLM 5.3 Flash Cyber.

Bring your agent.

Get an API key Set up opencode See the models