Model providers
One provider layer connects Silk Code to hosted APIs, local runtimes, and OpenAI-compatible endpoints.
Cloud example
export DEEPSEEK_API_KEY=sk-your-key
silkcode --model deepseek .Local example
# Install and start Ollama first
silkcode models pull qwen2.5-coder
silkcode --model auto .Provider groups
| Type | Providers |
|---|---|
| Cloud | DeepSeek, Qwen, Kimi, GLM, MiniMax, Cloudflare Workers AI, OpenRouter |
| Local | Ollama, vLLM, LM Studio |
| Custom | Any supported OpenAI-compatible endpoint configured with silkcode models add |