// API_DOCS.md

3 minutes to integrate. Drop-in OpenAI replacement.

01 Acquire API Key

sk-as-xxxxxxxxxxxxxxxxxxxxxxxx

02 Configure Endpoint

Set base_url. That's it.

# .env
OPENAI_API_KEY="sk-as-your-key"
OPENAI_BASE_URL="https://ai-space-station.com/v1"

03 Execute

cURL

curl https://ai-space-station.com/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer sk-as-your-key" \
  -d '{
    "model": "deepseek-chat",
    "messages": [{"role": "user", "content": "Hello, fleet."}]
  }'

Python

from openai import OpenAI

client = OpenAI(
    api_key="sk-as-your-key",
    base_url="https://ai-space-station.com/v1"
)

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Hello!"}]
)

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

JavaScript

import OpenAI from "openai";

const client = new OpenAI({
  apiKey: "sk-as-your-key",
  baseURL: "https://ai-space-station.com/v1",
});

const res = await client.chat.completions.create({
  model: "deepseek-chat",
  messages: [{ role: "user", content: "Hello!" }],
});

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

// FLEET REGISTRY

curl https://ai-space-station.com/v1/models \
  -H "Authorization: Bearer sk-as-your-key"

Model ID	Description	Context
`deepseek-chat`	DeepSeek-V3 — flagship reasoning	128K
`deepseek-reasoner`	DeepSeek-R1 — chain-of-thought	128K
`qwen-max`	Qwen-Max — 1M context (soon)	1M
`kimi-k2`	Kimi K2 — long-form (soon)	128K
`doubao-pro`	Doubao-Pro — fastest (soon)	256K

// STREAMING

All models support SSE streaming. Add stream: true:

response = client.chat.completions.create(
    model="deepseek-chat",
    messages=[{"role": "user", "content": "Count to 10"}],
    stream=True
)

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

// PAYMENT

We accept USDT (TRC-20). Stripe coming Q3.

Credits added instantly after 1 confirmation. Never expire.