DEVELOPERS

Keep your SDK.

ModelLane presents an OpenAI-compatible interface and translates between OpenAI, Anthropic, Gemini, and Responses-style APIs — so your existing SDK stays in place.

PYTHON

pythonOPENAI SDK

from openai import OpenAI

client = OpenAI(
    api_key=os.environ["MODELLANE_API_KEY"],
    base_url="https://api.modellane.app/v1"
)

response = client.responses.create(
    model="lane:production",
    input="..."
)

TYPE / JAVASCRIPT

typescript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.MODELLANE_API_KEY,
  baseURL: "https://api.modellane.app/v1",
});

const r = await client.responses.create({
  model: "lane:production",
  input: "...",
});

CURL

bash

curl https://api.modellane.app/v1/responses \
  -H "Authorization: Bearer $MODELLANE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model": "lane:production", "input": "..."}'

Because the endpoint is OpenAI-compatible, any OpenAI-compatible tooling works unchanged. See the API Reference for the full surface.