Quickstart
Create an account, get an API key, and send your first request to Engy.
This guide takes you from a new account to a successful inference request. It is intended for developers who are using Engy for the first time.
Prerequisites
Before you begin, make sure you have:
- An email address, or a Google or GitHub account
- A payment method for adding credits
curl, or Python 3.8 or later with theopenaipackage installed
Send your first request
Create an account
Go to engy.ai/signup and sign up with your email address, Google account, or GitHub account.
If you sign up with an email address, open the verification email and confirm your address before you sign in.
Add credits
In the dashboard, go to Credits and click Add credits. Choose an amount and a payment method, then complete the payment.
Engy uses prepaid credits. Each request is charged to your credit balance.
Create an API key
On the dashboard overview page, enter an optional label in the API keys section, and then click Create key.
Copy the key and store it securely. API keys start with sk-engy-.
The key is displayed only once. If you lose it, delete it and create a new key.
Set the key as an environment variable:
export ENGY_API_KEY="sk-engy-..."Send a request
Send a chat completion request to the Engy API:
curl https://api.engy.ai/v1/chat/completions \
-H "Authorization: Bearer $ENGY_API_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "glm-5.2",
"messages": [{"role": "user", "content": "Hello"}]
}'Understand the response
The response follows the OpenAI chat completion format. Engy adds the following information:
| Field or header | Description |
|---|---|
x_engy.request_id | The unique identifier of the request. Include it when you contact support. |
x_engy.charged_micro | The amount charged for the request, in micro-USD. One USD equals 1,000,000 micro-USD. |
X-Engy-Request-Id header | The same request identifier, returned as an HTTP header. |
X-Engy-Charged-Micro header | The same charged amount, returned as an HTTP header. |
Next steps
- Review your requests and spending on the Usage and Logs pages of the dashboard.
- Use any other model by changing the
modelparameter. For the available models, see Models and pricing. - Learn about streaming, tools, and other request options in Using the API.
- Connect a coding tool, such as Claude Code or Cursor.