Integrations

Use QuickSilver Pro from your favorite tool

Anything that speaks the OpenAI Chat Completions API works with QSP. Set base URL and key, pick a model, ship.

The two values you always need

Every tool below just wants these two strings — the rest of the config is the tool's own UI:

shell
Base URL  →  https://api.quicksilverpro.io/v1
API key   →  sk-...   (from your dashboard)

Don't see your tool below? Anything OpenAI-compatible works.

Aider (terminal pair-programmer)

Aider speaks OpenAI natively. Point it at QSP with two env vars and a model flag — that's it.

shell
export OPENAI_API_BASE="https://api.quicksilverpro.io/v1"
export OPENAI_API_KEY="$QSP_KEY"

aider --model openai/deepseek-v4-flash

The openai/ prefix tells Aider to route through the OpenAI client; everything after it is the QSP model ID (see the list).

Cline / Roo Code (VS Code agent)

Open the Cline (or Roo Code) sidebar → settings cog → API Provider:

text
API Provider:  OpenAI Compatible
Base URL:      https://api.quicksilverpro.io/v1
API Key:       <your QSP key>
Model ID:      deepseek-v4-pro   (or any QSP model)

Reasoning-by-default models (DeepSeek V4 Flash/Pro, R1, Qwen 3.6, Kimi K2.6) work as Cline's "Thinking" provider out of the box.

Continue.dev (VS Code / JetBrains)

Add QSP as a model in ~/.continue/config.json:

json
{
  "models": [
    {
      "title": "DeepSeek V4 Pro (QSP)",
      "provider": "openai",
      "model": "deepseek-v4-pro",
      "apiBase": "https://api.quicksilverpro.io/v1",
      "apiKey": "$QSP_KEY"
    }
  ]
}

Open WebUI

In Open WebUI: Admin Panel → Connections → OpenAI API, add a new connection:

text
URL:  https://api.quicksilverpro.io/v1
Key:  <your QSP key>

Save and reload — all 14 QSP models will appear in the model picker.

LobeChat

Settings → Language Model → enable OpenAI provider, then override:

text
API Proxy URL:  https://api.quicksilverpro.io/v1
API Key:        <your QSP key>
Model List:     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,
                gemini-3.1-pro-preview,gemini-3.5-flash,
                gemini-2.5-flash-image,gemini-3-pro-image-preview

Anything-LLM

Workspace → LLM Preference → Generic OpenAI:

text
Base URL:  https://api.quicksilverpro.io/v1
API Key:   <your QSP key>
Model:     deepseek-v4-flash   (or any QSP model)

Cursor (custom OpenAI endpoint)

Cursor Settings → Models → enable Override OpenAI Base URL:

text
Override OpenAI Base URL:  https://api.quicksilverpro.io/v1
OpenAI API Key:            <your QSP key>

Add the QSP model ID under Add custom model — Cursor will route through your override base URL for any custom model.

LangChain / LlamaIndex / Vercel AI SDK

Pass QSP's base URL into the OpenAI provider for any of these frameworks. Example (LangChain Python):

python
import os
from langchain_openai import ChatOpenAI

llm = ChatOpenAI(
    model="deepseek-v4-flash",
    base_url="https://api.quicksilverpro.io/v1",
    api_key=os.environ["QSP_KEY"],
)

Anything else

QSP is fully OpenAI-compatible — Chat Completions, streaming, tool calling, structured outputs, usage accounting. If your tool talks to api.openai.com/v1, changing base_url to https://api.quicksilverpro.io/v1 is almost always all you need.

Hit a snag? hello@quicksilverpro.io — we'll either help you wire it or fix the gateway.