OpenAI-Compatible API
The gateway implements the OpenAI Chat Completions / Embeddings protocol. Switch base_url and you're done.
Python
from openai import OpenAI
client = OpenAI(
api_key="cpk_xxx",
base_url="https://api.codepus.ai/v1",
)
resp = client.chat.completions.create(
model="gpt-4o-mini",
messages=[{"role": "user", "content": "hello"}],
)
print(resp.choices[0].message.content)
Node.js
import OpenAI from "openai";
const client = new OpenAI({
apiKey: "cpk_xxx",
baseURL: "https://api.codepus.ai/v1",
});
Supported fields
- ✅ messages, model, temperature, top_p, max_tokens
- ✅ stream (SSE)
- ✅ tools / tool_calls
- ✅ response_format (json_object / json_schema)
- ⚠️ Some fields are model-dependent
Routing
Use model: "auto" to let the gateway pick; or specify a concrete model. See Custom Base URL.