diff --git a/docs/customize/model-providers/more/quicksilverpro.mdx b/docs/customize/model-providers/more/quicksilverpro.mdx new file mode 100644 index 00000000000..229523cfe5c --- /dev/null +++ b/docs/customize/model-providers/more/quicksilverpro.mdx @@ -0,0 +1,61 @@ +--- +title: "QuickSilver Pro" +description: "Configure QuickSilver Pro with Continue to access 12 frontier open-source models (DeepSeek V4, R1, Qwen 3.6, Kimi K2.6, Gemini 3) through one OpenAI-compatible key" +--- + + + QuickSilver Pro is an OpenAI-compatible gateway for 12 frontier open-source + models: DeepSeek V4 Flash / V4 Pro / V3 / R1, Qwen 3.5 / 3.6, Kimi K2.6, + and the Gemini 2.5 / 3 family. ~20% under OpenRouter on the shared set. + + + + Get an API key from the [QuickSilver Pro dashboard](https://quicksilverpro.io/dashboard/). + + +## Configuration + +Because QuickSilver Pro speaks the OpenAI Chat Completions API, use the +`openai` provider with an `apiBase` override: + + + + ```yaml title="config.yaml" + name: My Config + version: 0.0.1 + schema: v1 + + models: + - name: DeepSeek V4 Pro (QSP) + provider: openai + model: deepseek-v4-pro + apiBase: https://api.quicksilverpro.io/v1 + apiKey: + ``` + + + ```json title="config.json" + { + "models": [ + { + "title": "DeepSeek V4 Pro (QSP)", + "provider": "openai", + "model": "deepseek-v4-pro", + "apiBase": "https://api.quicksilverpro.io/v1", + "apiKey": "" + } + ] + } + ``` + + + +Swap `model` for any of: +`deepseek-v4-flash`, `deepseek-v4-pro`, `deepseek-v3`, `deepseek-r1`, +`qwen3.6-35b`, `qwen3.5-35b`, `kimi-k2.6`, `gemini-2.5-flash`, +`gemini-2.5-flash-lite`, `gemini-3-flash-preview`. + + + Full model list, pricing, and integration tips for other tools: + [quicksilverpro.io/docs/integrations](https://quicksilverpro.io/docs/integrations/). +