Skip to main content

OpenCode

OpenCode is an open-source AI coding assistant available in terminal, web, and other forms. Although OpenCode natively supports a wide range of providers, pointing it to Tresor gives you:

  • Centralized management of different models and providers. No need to re-configure OpenCode when you switch LLM providers, just change the activated model in the alias group of Tresor.
  • No need to worry about the different API format underlying model is using, Tresor will auto-translate between the OpenAI API (OpenCode) to other API formats (e.g., Anthropic messages for Claude models).

However, it also comes with drawbacks:

  • If you use alias to map model names in Tresor, it will lead to less precise control over model-specific configurations, like the reasoning effort and context length.

This page shows how to wire OpenCode to Tresor.

✅ Prerequisites​

1. Configure Tresor​

There are two ways to prepare Tresor:

1.1 Option 1: via Web UI​

Web UI is more intuitive, but require more manual operations.

  1. In "Downstreams" tab

    • Click + Add Provider to add the LLM provider you are about to use.

  2. In "Aliases" tab

    • Click + New Alias Group
      • Input Model ID: model-opencode
      • Leave "Regex Pattern" unchecked.
      • Select the Downstream and Output Model IDs you added previously.

  3. In "Settings" tab

    • Click + Add API Key under "Proxy Authentication" section (e.g, sk-proxy-123). Copy it, and we are about to fill it into apiKey in the following section.

1.2 Option 2: via config.yaml​

Editing yaml is less intuitive, but require less manual operations.

The following example config.yaml uses 3 downstream providers. Replace them based on your actual providers.

~/.config/tresor/config.yaml
bind_addr: 127.0.0.1:11510
proxy_api_keys:
  - sk-proxy-123
... # Omitted showing other settings here
downstreams:
    - id: llama-cpp
      name: llama.cpp
      base_url: http://127.0.0.1:3000 # change to your actual llama.cpp listening port
      api_formats:
        - openai
        - anthropic
      output_model_ids:
        - qwen3.6:27b-mtp:instruct
    - id: deepseek
      name: DeepSeek
      base_url: https://api.deepseek.com/anthropic
      api_formats:
        - anthropic
      output_model_ids:
        - deepseek-v4-flash
        - deepseek-v4-pro
    - id: minimax
      name: MiniMax
      base_url: https://api.minimaxi.com/anthropic
      api_formats:
        - anthropic
      output_model_ids:
        - MiniMax-M2.5
        - MiniMax-M2.7
        - MiniMax-M3
aliases:
    - input_model_id: model-opencode
      options:
        - id: alias-deepseek-pro
          downstream_id: deepseek
          output_model_id: deepseek-v4-pro
        - id: alias-deepseek-flash
          downstream_id: deepseek
          output_model_id: deepseek-v4-flash
        - id: alias-minimax-m3
          downstream_id: minimax
          output_model_id: MiniMax-M3
        - id: alias-llama-cpp-qwen-instruct
          downstream_id: llama-cpp
          output_model_id: qwen3.6:27b-mtp:instruct

Restart Tresor to apply the changes in yaml.

2. Configure OpenCode​

OpenCode supports connecting to OpenAI-compatible endpoints. Point it at your Tresor instance:

~/.config/opencode/opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "provider": {
    "Tresor": {
      "npm": "@ai-sdk/openai-compatible",
      "name": "Tresor (local)",
      "options": {
        "baseURL": "http://127.0.0.1:11510/v1",
        "apiKey": "sk-proxy-123"
      },
      "models": {
        "model-opencode": {
          "name": "model-opencode (local)",
          "limit": {
            "context": 262144,
            "output": 32000
          }
        }
      }
    }
  }
}

3. Launch OpenCode​

cd /path/to/my-project
opencode

OpenCode will send the model name model-opencode to Tresor, which will forward the request to the active downstream for that alias.

4. Hot-switch from the web UI​

Open http://127.0.0.1:11510 in a browser, go to the Aliases tab, and click any sibling option card to make it active. OpenCode's next request will be routed to the new downstream — no restart of either Tresor or OpenCode is required. 🎉

For example, flip model-opencode from deepseek-v4-pro to MiniMax-M3 with a single click, and the agent immediately starts using MiniMax on the following turn.

🔧 Troubleshooting​

SymptomLikely causeFix
401 Unauthorized from Tresorproxy_api_keys is set but apiKey doesn't matchSet apiKey to one of the keys in proxy_api_keys, or empty the list in config.yaml

📚 See also​