One API · every model
No rewriting code for every provider. SalpX is compatible with the OpenAI SDK: point base_url at SalpX and call Claude, Gemini, Qwen, DeepSeek, Kimi and more.
// just point base_url at SalpXimport OpenAI from "openai"; const ai = new OpenAI({ baseURL: "https://www.salpx.com/v1", apiKey: process.env.SALPX_KEY,}); const r = await ai.chat.completions.create({ model: "claude-opus-4-8", messages: [{ role: "user", content: "Hi" }],});
from openai import OpenAI client = OpenAI( api_key="sk-••••••••••••", base_url="https://www.salpx.com/v1", # the only line you change) resp = client.chat.completions.create( model="gpt-5.6-sol", messages=[{"role": "user", "content": "Hello, SalpX"}],)
curl https://www.salpx.com/v1/chat/completions \ -H "Authorization: Bearer $SALPX_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "gemini-3.5-flash", "messages": [{"role": "user", "content": "Hi"}] }'