VCodeX
Getting started

Make your first request

Call the gateway directly with curl or the OpenAI SDK.

The gateway is OpenAI-compatible, so any OpenAI client works once you set the base URL and a VCodeX key.

curl

curl https://app.vcodex.ai/v1/chat/completions \
  -H "Authorization: Bearer $VCODEX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "vcodex/auto",
    "messages": [{ "role": "user", "content": "ship it" }]
  }'

Python (OpenAI SDK)

from openai import OpenAI

client = OpenAI(
    base_url="https://app.vcodex.ai/v1",
    api_key="$VCODEX_KEY",
)

resp = client.chat.completions.create(
    model="vcodex/auto",
    messages=[{"role": "user", "content": "ship it"}],
    stream=True,
)
for chunk in resp:
    print(chunk.choices[0].delta.content or "", end="")

TypeScript (OpenAI SDK)

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://app.vcodex.ai/v1",
  apiKey: process.env.VCODEX_KEY,
});

const resp = await client.chat.completions.create({
  model: "vcodex/auto",
  messages: [{ role: "user", content: "ship it" }],
});

Model selection

Use vcodex/auto to let the gateway pick a tier, or pass a concrete model id from GET /v1/models.

On this page