GLM 5.3in opencode

Yes. GLM 5.3 Uncensored runs in opencode through this endpoint as glm-5.3-uncensored, at $2.00 per million input tokens and $5.00 per million output tokens ($1.00 for cached input). Full-size GLM for long reasoning. The full GLM 5.3, uncensored: frontier reasoning, a million tokens of context and tool calling, with no refusals. Text only: it does not take images.

Model id: glm-5.3-uncensored
Build: Uncensored
Context: 1M tokens
Tools / reasoning / images: Yes / Yes / No
Per million tokens: $2.00 in / $5.00 out
Base model score: 45 on Artificial Analysis

Where it fits

The full GLM 5.3 rather than the Flash build: slower, and stronger on long chains of reasoning over a large codebase. Reach for it when a session is mostly reading and deciding, such as an architecture review or a migration plan.

What to watch for

It is text only. Its entry in the config sets "attachment" to false so opencode does not offer to send it images; paste a screenshot and you want one of the Flash models or Kimi instead.

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-uncensored": {
          "name": "GLM 5.3 Uncensored",
          "tool_call": true,
          "reasoning": true,
          "attachment": false,
          "limit": { "context": 1048576, "output": 32000 }
        }
      }
    }
  },
  "model": "uncensored-opencode/glm-5.3-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-uncensored "Review the architecture of this repository and write the risks you see into REVIEW.md"

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, 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