Quickstart
Integrate Tokensmart and make your first API call in under 5 minutes.
Step 1: Sign up
Go to the login page and sign up with your email. New users automatically receive a welcome credit.
Step 2: Create an API key
- Open the API Keys page
- Click "Create new key"
- Give it a name (for example
my-app-dev) - Save the key that appears — it starts with
pk_live_and is only shown once
⚠️ API keys are like passwords. If one leaks, delete and regenerate it immediately.
Step 3: Make your first request
Test it with curl:
curl https://api.tokensmart.ai/v1/chat/completions \
-H "Content-Type: application/json" \
-H "Authorization: Bearer pk_live_xxxxxxxxxxxxxxxx" \
-d '{
"model": "gpt-5.5",
"messages": [
{ "role": "user", "content": "Hello, Tokensmart!" }
]
}'
You should get a JSON response in exactly the same format OpenAI returns.
Step 4: Use an SDK
If your project uses the OpenAI Python SDK:
from openai import OpenAI
client = OpenAI(
api_key="pk_live_xxxxxxxxxxxxxxxx",
base_url="https://api.tokensmart.ai/v1",
)
resp = client.chat.completions.create(
model="claude-sonnet-4-6", # Yes, you can call Claude too!
messages=[{"role": "user", "content": "Write me a limerick"}],
)
print(resp.choices[0].message.content)
That is it. You can now switch between OpenAI and Claude inside the same SDK without changing any code.
Next steps
- Authentication details — more API key options
- Model list — see all supported models
- Pricing — per-model rates