Developer documentation

Quickstart

1. Create an accountSign up and verify your email.
2. Create an API keyOpen Dashboard → API keys. The full key is shown once.
3. Make a requestUse the base URL and a model ID returned by /v1/models.

curl https://vicecityai.shop/v1/chat/completions \
  -H "Authorization: Bearer vc_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": false
  }'

Authentication

Send your ViceCityAI key as a Bearer token on every API request. Keep it on the server and never expose it in browser code or public repositories.

Authorization: Bearer vc_your_api_key_here

Models

Use the live models endpoint as the source of truth. The catalog may change when upstream availability changes. Prices and observed uptime are shown on the Pricing page.

curl https://vicecityai.shop/v1/models \
  -H "Authorization: Bearer vc_your_api_key_here"

Chat and streaming

POST /v1/chat/completions

The request format follows OpenAI Chat Completions. Set stream to true for Server-Sent Events; the stream ends with data: [DONE].

curl -N https://vicecityai.shop/v1/chat/completions \
  -H "Authorization: Bearer vc_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5",
    "messages": [
      {"role": "system", "content": "Be concise."},
      {"role": "user", "content": "Explain SSE."}
    ],
    "stream": true
  }'

Common fields

Vision

For vision-capable models, send message content as an array containing text and an image_url. ViceCityAI currently accepts PNG, JPEG and WebP data URLs through this endpoint.

{
  "model": "openai/gpt-5",
  "messages": [{
    "role": "user",
    "content": [
      {"type": "text", "text": "Describe this image"},
      {"type": "image_url", "image_url": {
        "url": "data:image/png;base64,..."
      }}
    ]
  }]
}

Images and video

Check the live model catalog before use. Media availability and accepted parameters differ by model.

SDK examples

Python

from openai import OpenAI

client = OpenAI(
    api_key="vc_your_api_key_here",
    base_url="https://vicecityai.shop/v1"
)

response = client.chat.completions.create(
    model="openai/gpt-5",
    messages=[{"role": "user", "content": "Hello!"}]
)
print(response.choices[0].message.content)

Node.js

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "vc_your_api_key_here",
  baseURL: "https://vicecityai.shop/v1"
});

const response = await client.chat.completions.create({
  model: "openai/gpt-5",
  messages: [{ role: "user", content: "Hello!" }]
});
console.log(response.choices[0].message.content);

Integrations

Use the OpenAI-compatible option in tools that allow a custom base URL. Exact settings and supported features depend on the client.

Billing

Usage is charged from your prepaid balance after a successful request. Text-model cost is calculated from input and output token usage at the prices shown on the Pricing page.

cost = (input_tokens × input_price + output_tokens × output_price) / 1,000,000

Errors

Limits and behavior

• Request body: up to 2 MB.
• Maximum requested output: 32,768 tokens; a model may enforce a lower limit.
• Model context windows and availability depend on the active upstream route.
• Do not automatically retry validation, authentication or billing errors.