Getting started
A simple first test
Three steps to
your first request.
Start with what you are building and choose a model for that workload. Then get your API key and use it in the model’s test.
Choose your workload.
Compare models for the task you want to build.
Get your API key.
Get API access to receive your own Roten key.
Replace the API key and run.
Use your own API key in the model test. The remaining request settings are ready to use.
Implementation
Copy a model test.
Choose a model, then copy its Python or cURL test. Only replace the API-key placeholder.
API model ID: glm-5.3-flash
Text and coding through the text API. Input format: text.
Copy the Python or cURL test for GLM-5.3 Flash. Replace the API-key placeholder with your own key and run.
Basic text test · Sends a basic text request. Vision input is not confirmed for this upstream model.
import requests
response = requests.post(
url="https://api.roten-ai.com/v1/chat/completions",
headers={
"Authorization": "Bearer YOUR_ROTEN_API_KEY",
},
json={
"model": "glm-5.3-flash",
"messages": [
{
"role": "user",
"content": "Explain what an API key is in one short sentence."
}
],
"max_tokens": 128,
"thinking": {
"type": "disabled"
},
"stream": False
},
timeout=180,
)
print(response.json())
response.raise_for_status()curl --fail-with-body 'https://api.roten-ai.com/v1/chat/completions' \
-H 'Content-Type: application/json' \
-H 'Authorization: Bearer YOUR_ROTEN_API_KEY' \
-d '{
"model": "glm-5.3-flash",
"messages": [
{
"role": "user",
"content": "Explain what an API key is in one short sentence."
}
],
"max_tokens": 128,
"thinking": {
"type": "disabled"
},
"stream": false
}'Python requires requests: install once with python3 -m pip install requests. cURL examples run directly in your terminal.
Find the right model
Start with your workload.
Explore the models and their prices, or compare the performance and value choices for your task.
Build with Roten
Ready to get your API key?
Choose your workload, then request API access to get started.