OpenCode with our models: a ready config in a minute

Why connect it

OpenCode supports any OpenAI-compatible provider. Describe the tenzo provider in opencode.json and pick a model.

You can list several models in the config and switch between them right inside OpenCode.

How to connect OpenCode

You need a key from the dashboard: 3 free hours start right after sign-up. Replace tc-your-key with your key.

1. 1

   Get a key

   Create a key in the dashboard and store it in TENZO_API_KEY.

   terminalCopy

   export TENZO_API_KEY=tc-your-key

2. 2

   Create the config

   Create opencode.json in the project root or in ~/.config/opencode/ and paste the config.

   opencode.jsonCopy

   {
     "$schema": "https://opencode.ai/config.json",
     "provider": {
       "tenzo": {
         "npm": "@ai-sdk/openai-compatible",
         "name": "Tenzo Cloud",
         "options": {
           "baseURL": "https://tenzo-cloud.com/v1",
           "apiKey": "{env:TENZO_API_KEY}"
         },
         "models": {
           "glm-5.3": {
             "name": "GLM 5.3"
           },
           "qwen-3.8-max": {
             "name": "Qwen 3.8 Max"
           }
         }
       }
     },
     "model": "tenzo/glm-5.3"
   }

3. 3

   Run opencode

   Pick a model from the tenzo provider and send your first request.

Common errors and fixes

OpenCode does not see the provider

Check that the file is named opencode.json, sits in the project root or ~/.config/opencode/, and the JSON has no trailing commas.

401 invalid_api_key, “key not found”

Make sure the whole key is copied with no spaces or quotes and is enabled in the dashboard. Expired keys also return 401.

403 no_access, “no access to this model”

There is no active subscription for this model, or the key does not allow this model or your IP. Check Plans and the key restrictions in the dashboard.

404 model_not_found

The model id is wrong. Use an id from the model list, for example qwen-3.8-max or glm-5.3.

429 concurrency_limit

All your streams are busy or you exceeded 120 requests a minute. Retry in a few seconds or buy more streams, they stack.

503 model_unavailable

The model is under maintenance. Each model’s status is on the status page; switch models with one line.