API Documentation

API Dashboard →

Our API is OpenAI-compatible. You can use it directly with Cursor, VS Code, or any OpenAI SDK. Authenticate using an API key from your API Dashboard.

Base URL

https://voidshift.uk/api/v1

Authentication

Pass your API key in the Authorization header:

Authorization: Bearer <YOUR_API_KEY>

Chat Completions

POST /chat/completions – OpenAI-compatible request/response. Streaming supported via stream=true.

JSON request

{
  "model": "deepseek/deepseek-r1-distill-llama-70b",
  "messages": [
    { "role": "system", "content": "You are a helpful coding assistant." },
    { "role": "user", "content": "Write a Python function to reverse a string." }
  ],
  "temperature": 0.2,
  "stream": false
}

Curl

curl -s https://voidshift.uk/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "model": "deepseek/deepseek-r1-distill-llama-70b",
    "messages": [
      {"role":"user","content":"Hello from voidshift!"}
    ]
  }'

Streaming

curl https://voidshift.uk/api/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer $YOUR_API_KEY" \
  -d '{
    "stream": true,
    "messages": [{"role":"user","content":"Stream this response."}]
  }'

Using with Cursor

Create a Custom API Provider in Cursor:

  1. Open Settings → Features → Models → "Add Custom Model".
  2. Base URL: https://voidshift.uk/api/v1
  3. API Key: your key from the API Dashboard.
  4. Model: deepseek/deepseek-r1-distill-llama-70b (or any model returned by /models).

Cursor calls the OpenAI Chat Completions API; our endpoint matches that spec and routes to HuggingFace under the hood.

Models

GET /models – lists available models in OpenAI format.

curl -s https://voidshift.uk/api/v1/models \
  -H "Authorization: Bearer $YOUR_API_KEY"

Need help? Contact support.