OpenCode

OpenCode is an open source AI coding assistant that runs in your terminal. It supports OpenAI-compatible APIs.

Configuration

Set these environment variables:

export OPENAI_API_KEY="ky-your-api-key"
export OPENAI_BASE_URL="https://kymaapi.com/v1"

Then run:

opencode --model qwen-3.6-plus

Or configure in your settings file:

{
  "provider": "openai",
  "base_url": "https://kymaapi.com/v1",
  "api_key": "ky-your-api-key",
  "model": "qwen-3.6-plus"
}

Recommended Models

Model	Alias	Best For
`qwen-3.6-plus`	`best`	Recommended — highest quality
`qwen-3-coder`	`code`	Best alias for code-focused tasks
`kimi-k2.6`	`agent`	Best tool calling, 262K context
`qwen-3-32b`	`fast`	Ultra-fast active coding model
`deepseek-v4-pro`	—	1M context, top reasoning. Complex refactors and long-codebase tasks.
`deepseek-v4-flash`	—	1M context, value tier. Everyday completions where speed matters.

curl "https://kymaapi.com/v1/models/recommend?agent=opencode"

See all model aliases for shortcuts.

Prompt Caching

Prompt caching is automatic. Your system prompt and tool definitions are cached for 5 minutes, and the repeated part then bills at that model’s cached-input rate instead of its input rate. No code changes needed. See Prompt Caching for details.

Guides

Use Cases

Integrations

Configuration

Recommended Models

Prompt Caching

​Configuration

​Recommended Models

​Prompt Caching

Configuration

Recommended Models

Prompt Caching