STEP 01
Create an account
Register at the TokenRoc console and sign in.
01 / Setup
Send your first request
Create an account, generate a key, and choose a model from the live pricing catalog. Never expose an API key in browser or mobile client code.
STEP 02
Generate a key
Open API Keys, create a token, and store it in a server-side secret.
STEP 03
Choose a model
Use the exact identifier shown in the live model catalog.
02 / cURL
Chat completions request
Set your key as an environment variable and send the same JSON shape used by OpenAI-compatible clients.
terminalPOST /v1/chat/completions
curl https://api.tokenroc.com/v1/chat/completions \
-H "Authorization: Bearer $TOKENROC_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "deepseek-v3.2",
"messages": [
{"role": "user", "content": "Say hello in one sentence."}
]
}'Model availability changes over time. Copy the model identifier from the live pricing page instead of hard-coding a display name.
03 / Python
Use the OpenAI SDK
Only the credentials and base URL are TokenRoc-specific. The client call remains OpenAI-compatible.
app.pyPython
import os
from openai import OpenAI
client = OpenAI(
api_key=os.environ["TOKENROC_API_KEY"],
base_url="https://api.tokenroc.com/v1",
)
response = client.chat.completions.create(
model="deepseek-v3.2",
messages=[{"role": "user", "content": "Say hello in one sentence."}],
)
print(response.choices[0].message.content)04 / Reference
Core endpoints
Support varies by model and upstream provider. Start with the model catalog, then use the endpoint supported by that model.
| Method | Endpoint | Purpose |
|---|---|---|
| GET | /v1/models | List models available to the current API key. |
| POST | /v1/chat/completions | Create a standard or streaming chat completion. |
| POST | /v1/responses | Use the Responses-compatible request format where supported. |
05 / Troubleshooting
Common HTTP responses
| Status | Meaning | What to check |
|---|---|---|
| 401 | Authentication failed | Confirm the Bearer token is present, active, and copied without spaces. |
| 403 | Access or balance rejected | Check wallet balance, key permissions, and model access. |
| 429 | Rate or quota limit | Reduce concurrency, apply backoff, or review token limits. |
| 5xx | Gateway or upstream failure | Retry with exponential backoff and check the status page. |
06 / Next