API Documentation

TokenShop exposes an OpenAI-compatible API. Any OpenAI SDK works — just change the base URL and API key. Usage is metered per token and charged against your prepaid balance.

1. Register (get key + trial credit)

curl -X POST https://tokshop.xyz/api/auth/register \
  -H "Content-Type: application/json" \
  -d '{"email":"you@example.com"}'

2. List models & pricing

curl https://tokshop.xyz/v1/models

3. Chat completions (non-stream)

curl -X POST https://tokshop.xyz/v1/chat/completions \
  -H "Authorization: Bearer tk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek/deepseek-v3.2",
    "messages": [{"role": "user", "content": "Hello!"}],
    "max_tokens": 100
  }'

4. Streaming

curl -N -X POST https://tokshop.xyz/v1/chat/completions \
  -H "Authorization: Bearer tk_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"deepseek/deepseek-v3.2","messages":[{"role":"user","content":"Hi"}],"stream":true}'

Streaming responses include a final usage chunk; billing uses exact token counts from the provider.

5. OpenAI SDK (Python)

from openai import OpenAI
client = OpenAI(base_url="https://tokshop.xyz/v1", api_key="tk_YOUR_KEY")
r = client.chat.completions.create(
    model="deepseek/deepseek-v3.2",
    messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)

6. Account & balance

curl https://tokshop.xyz/api/account -H "Authorization: Bearer tk_YOUR_KEY"

Errors

401 invalid_api_key — key missing/rotated/inactive
402 insufficient_quota — balance below $0.001, top up at /pricing
404 model_not_found — check GET /v1/models
502 server_error — upstream failure (not billed)

Data policy

We store only metering metadata (token counts, model, timestamps). Prompt and completion contents are not persisted by TokenShop. Payments currently run in clearly-labeled TEST MODE.