Quickstart
You can go from zero to a billed completion in a few minutes.
1. Create an account
Open Register. New accounts receive 1,000,000 free tokens. No card required.
2. Create an API key
Sign in, open API Keys, and mint a key. The full sk-… secret is shown once. Store it like a password. The dashboard only keeps a hash and an 8-character prefix.
3. Point any OpenAI client at the proxy
export OPENAI_BASE_URL=https://api.proxy.gonka.gg/v1
export OPENAI_API_KEY=sk-your-api-key-herePython:
from openai import OpenAI
client = OpenAI(
base_url="https://api.proxy.gonka.gg/v1",
api_key="sk-your-api-key-here",
)
print(client.models.list())4. Send a completion
Use a model id from GET /v1/models. Do not guess old names (Kimi is gone).
curl https://api.proxy.gonka.gg/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer sk-your-api-key-here" \
-d '{
"model": "deepseek-ai/DeepSeek-V4-Flash-0731",
"messages": [{"role": "user", "content": "Say hello in one sentence."}]
}'5. Watch usage
Usage shows tokens and cost. During the free grant the dashboard balance reads like 12K/1M. After that it shows USD credit.
Next
- Authentication
- OpenAI SDK
- Agents and IDEs
- Top up when the free grant is gone