OpenCode
Prepare API
Before configuration, make sure you have the following information:
API Key
A string of your created API Key.
Base URL
Address: https://api.jalapeno-cloud.ai/v1
Important: Must include the trailing /v1
Model Name
Copy the full model name from the Model Marketplace, e.g., DeepSeek-V4-Pro
Install OpenCode
Download and install through OpenCode official channels. OpenCode
Linux / macOS / WSL2
curl -fsSL https://opencode.ai/install | bash
Or install via npm:
npm install -g opencode-ai
Windows
OpenCode recommends WSL2 for the best experience. Install inside WSL2 using the Linux command above.
For native Windows, install via Chocolatey or Scoop:
choco install opencode
# or
scoop install opencode
Or install via npm:
npm install -g opencode-ai
Connect OpenCode
OpenCode routes requests through a custom provider defined in ~/.config/opencode/opencode.json.
Edit Configuration File
Create or edit ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"model": "jalapeno/GLM-5.1",
"provider": {
"jalapeno": {
"npm": "@ai-sdk/openai-compatible",
"name": "Jalapeno Cloud",
"options": {
"baseURL": "https://api.jalapeno-cloud.ai/v1",
"apiKey": "{env:JALAPENO_API_KEY}"
},
"models": {
"GLM-5.1": {
"name": "GLM-5.1"
},
"DeepSeek-V4-Pro": {
"name": "DeepSeek-V4-Pro"
},
"MiniMax-M2.7": {
"name": "MiniMax-M2.7"
}
}
}
}
}
Field Description
| Field | Description |
|---|---|
model | Default model in provider/model format (e.g., jalapeno/GLM-5.1) |
npm | AI SDK package; use @ai-sdk/openai-compatible for /v1/chat/completions |
name | Display name for the provider |
options.baseURL | API endpoint, must include trailing /v1 |
options.apiKey | API key; use {env:VAR_NAME} to read from an environment variable |
models | Model IDs available from the Model Marketplace |
Note: The top-level model field is required. Model IDs under models must match names from the Model Marketplace.
Set API Key
Export your API key before running OpenCode:
export JALAPENO_API_KEY="your-api-key"
Add the export line to your shell profile (e.g. ~/.bashrc or ~/.zshrc) to persist it across sessions.
Alternatively, run opencode providers login, choose Other, enter provider ID jalapeno, and paste your API key.
Switch Model
Change the top-level model field, or pass -m on the command line:
"model": "jalapeno/DeepSeek-V4-Pro"
Verify Connection
With JALAPENO_API_KEY exported, run:
opencode run -m jalapeno/GLM-5.1 "Reply with exactly one word: hello"
A successful run returns pong.
Use Model
Start the interactive TUI in your project directory:
opencode
Use /models in the TUI to switch models.