Start sending requests

Quickstart

1. Create an account and open your project.
2. Create an API key under API Keys.
3. Send a request to https://api.digitspace.cn/v1:

curl https://api.digitspace.cn/v1/chat/completions \
  -H "Authorization: Bearer $DIGITSPACE_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{ "role": "user", "content": "Say hello in three languages." }]
  }'

Authentication

Every request needs your key in the Authorization header as a bearer token. Keep keys on your server; never ship them in a browser or mobile app. You can revoke a key at any time from the dashboard, and requests made with it stop immediately.

Using an SDK

Any OpenAI-compatible client works. Point it at DigitSpace:

JavaScript / TypeScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: process.env.DIGITSPACE_API_KEY,
  baseURL: "https://api.digitspace.cn/v1",
});

const reply = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Write a haiku about routing." }],
});

console.log(reply.choices[0].message.content);

Python

from openai import OpenAI
import os

client = OpenAI(
    api_key=os.environ["DIGITSPACE_API_KEY"],
    base_url="https://api.digitspace.cn/v1",
)

reply = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Write a haiku about routing."}],
)

print(reply.choices[0].message.content)

Choosing a model

Pass any model ID from the models page to use that model, for example gpt-4o. DigitSpace sends it to a healthy provider that serves it and falls back to another one if the first fails.

Pass auto to let DigitSpace choose: it looks at what the request needs (context length, tools, images, reasoning) and picks the lowest-priced model that can handle it. You can list every available model with GET https://api.digitspace.cn/v1/models.

Streaming

Set stream: true to receive the reply as server-sent events while it is generated, exactly as with OpenAI. SDKs handle this for you:

const stream = await client.chat.completions.create({
  model: "auto",
  messages: [{ role: "user", content: "Count to five." }],
  stream: true,
});

for await (const chunk of stream) {
  process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}

Billing modes

• Credits: top up your balance and pay provider rates per request, plus a flat fee on each top-up.
• Your own keys: add your provider keys in the dashboard and pay providers directly. Routing and usage tracking are free.

Every request appears under Activity with its model, provider, tokens, latency and cost. See pricing.

Errors

Errors use the OpenAI error format, with a message that explains what went wrong. The most common status codes:

Getting help

Questions or problems? Contact us or email support@digitspace.cn.