GLM 5.3 Flashin opencode

Yes. GLM 5.3 Flash Uncensored runs in opencode through this endpoint as glm-5.3-flash-uncensored, at $0.30 per million input tokens and $1.00 per million output tokens ($0.20 for cached input). The default pick for opencode. A million tokens of context, tool calling and vision, with no refusals. Point a coding agent at it.

Model id: glm-5.3-flash-uncensored
Build: Uncensored
Context: 1M tokens
Tools / reasoning / images: Yes / Yes / Yes
Per million tokens: $0.30 in / $1.00 out
Base model score: 42 on Artificial Analysis

Where it fits

This is the model the config on this site sets as the default, because it is the balance most coding sessions want: it calls tools, it reads screenshots and diagrams you paste into the session, it reasons before it edits, and it keeps a million tokens of the repository in view. Start here and move up to Kimi K3.1 Pro only when a task is hard enough to need it.

What to watch for

It thinks before every answer, so short one-line questions come back a little slower than on a model without reasoning.

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": {
        "glm-5.3-flash-uncensored": {
          "name": "GLM 5.3 Flash Uncensored",
          "tool_call": true,
          "reasoning": true,
          "attachment": true,
          "limit": { "context": 1048576, "output": 32000 }
        }
      }
    }
  },
  "model": "uncensored-opencode/glm-5.3-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/glm-5.3-flash-uncensored "Read the failing test in this repo, find the cause 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: Kimi K3.1 Pro, 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