OpenCode
~/.config/opencode/opencode.json
OpenCode is provider-agnostic and works best when you supply your own key. Add an openai-compatible provider entry, then select the model inside the TUI. Because it consumes the whole session rather than a single completion, it is one of the better showcases for cache-aware routing.
Code
{ "provider": { "starsea": {
"npm": "@ai-sdk/openai-compatible",
"options": { "baseURL": "https://starseaapi.com", "apiKey": "sk-your-key" },
"models": { "deepseek-v4.1-flash": {} } } } }Quickstart
Create an API key
Sign up, then create a token in the console. A key works across the whole catalogue; scope and quota can be restricted per key.
Point your client at the endpoint
Set base_url to https://starseaapi.com/v1 and use the key. Any OpenAI-compatible SDK, IDE or desktop client works.
Pick a model
Start with a low-cost tier for prototyping. Every id in the catalogue can be swapped without touching code.
Watch cost, not just quality
Output tokens are usually priced at a multiple of input, and reasoning models emit thinking tokens. Keep stable prompt prefixes first so caching applies.
Integrations
Claude Code
ANTHROPIC_BASE_URL / ANTHROPIC_AUTH_TOKEN
↗Cursor
Settings → Models → OpenAI API Key
↗Cline (VS Code)
OpenAI Compatible provider
↗Roo Code
OpenAI Compatible provider
↗Continue
~/.continue/config.json
↗Aider
--openai-api-base
↗Zed
settings.json → language_models
↗Kilo Code
OpenAI Compatible provider
↗