Quick start

You will be making calls in about a minute.

1Create an API key

2Point your client at the base URL

Any OpenAI-compatible client works. Only the base URL and key change.

Base URL: https://api.voyai.net/v1

3Make a call

curl https://api.voyai.net/v1/chat/completions \
  -H "Authorization: Bearer $VOYAI_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V3.2",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

cURL

import os
from openai import OpenAI

client = OpenAI(
    base_url="https://api.voyai.net/v1",
    api_key=os.environ["VOYAI_API_KEY"],
)

resp = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(resp.choices[0].message.content)

Python · openai

import OpenAI from "openai";

const client = new OpenAI({
  baseURL: "https://api.voyai.net/v1",
  apiKey: process.env.VOYAI_API_KEY,
});

const resp = await client.chat.completions.create({
  model: "deepseek-ai/DeepSeek-V3.2",
  messages: [{ role: "user", content: "Hello" }],
});
console.log(resp.choices[0].message.content);

Node · openai

Streaming

Set stream: true. Responses arrive as standard SSE chunks, and usage is reported in the final chunk so your bill matches exactly what was generated.

stream = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",
    messages=[{"role": "user", "content": "Write a haiku"}],
    stream=True,
)

for chunk in stream:
    if chunk.choices and chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

Errors

Errors follow the OpenAI error shape, so existing error handling keeps working.

Code	Meaning
401	API key is missing, invalid or expired.
402	Balance exhausted, or this key hit its spend limit.
404	Unknown model ID, or the key is not permitted to use it.
429	Rate limit or concurrency limit reached. Back off and retry.
503	All upstream channels for this model are down. Retry shortly.