2026 — 2035
Era of Compute Equality

1. Install the "Continue" extension from the VS Code Marketplace
2. Open command palette → "Continue: Open Config (JSON)"
3. Paste the configuration below, replace YOUR_API_KEY with your key

{
  "models": [
    {
      "title": "TKNC Miner",
      "provider": "openai",
      "model": "tknc-miner-model",
      "apiKey": "YOUR_API_KEY",
      "apiBase": "http://127.0.0.1:9393/v1"
    }
  ]
}

Tip: If your IDE cannot resolve IPv6 URLs, start the tkncd built-in proxy — see the IPv6 Bridge section below.

1. Open Cursor → Settings → Models → "Add Model"
2. Provider: select "OpenAI"
3. Fill in Base URL, API Key, and Model name as shown

1. Settings → AI Providers → Custom OpenAI-compatible
2. Use the built-in tkncd proxy on port 9393 as the endpoint
3. Both /v1/chat/completions and /chat/completions paths are supported

Base URL:  http://127.0.0.1:9393/v1
API Key:   tknc_xxxxxxxxxxxxxxxxxxxxxx
Model:     tknc-miner-model

1. Open Continue config at ~/.continue/config.json
2. Add the TKNC provider to your models array
3. Restart the Continue extension — done

{
  "models": [
    {
      "model": "tknc-miner-model",
      "contextLength": 8192,
      "apiKey": "YOUR_API_KEY",
      "apiBase": "http://127.0.0.1:9393/v1",
      "provider": "openai",
      "title": "TKNC Miner",
      "completionOptions": { "temperature": 0.7 }
    }
  ],
  "tabAutocompleteModel": {
    "title": "TKNC Miner",
    "provider": "openai",
    "model": "tknc-miner-model",
    "apiKey": "YOUR_API_KEY",
    "apiBase": "http://127.0.0.1:9393/v1"
  }
}

Drop-in replacement for any code using the official openai package. Just change base_url.

from openai import OpenAI

client = OpenAI(
    api_key="YOUR_API_KEY",
    base_url="http://127.0.0.1:9393/v1",
)

stream = client.chat.completions.create(
    model="tknc-miner-model",
    messages=[{"role": "user", "content": "Write a quicksort in Python"}],
    stream=True,
    max_tokens=500,
)

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

Verify connectivity and streaming in one command.

curl -N -X POST http://127.0.0.1:9393/v1/chat/completions \
  -H "Content-Type: application/json" \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -d '{
    "model": "tknc-miner-model",
    "messages": [{"role":"user","content":"Hello!"}],
    "stream": true,
    "max_tokens": 50
  }'