There are only three key steps to invoking the model through the API:
1. Obtaining access credentials
- After registering an account in theAPI ManagementPage Generate Exclusive Key
- key inBearer TokenAuthentication in the form of
2. Configuring API requests
curl -X POST https://llm.chutes.ai/v1/chat/completions
-H "Content-Type: application/json"
-H "Authorization: Bearer YOUR_API_KEY"
-d '{
"model": "deepseek-ai/DeepSeek-V3",
"messages": [{"role": "user", "content": " explain quantum computing"}]
}'
3. Designation of target models
- In the request body's
modelFields are populated with model identifiers supported by the platform. - for example
"model": "deepseek-ai/DeepSeek-V3"
For those who needGeneral Templatesscenarios, the API endpoint can be set in a third-party application such as JanitorAI as ahttps://llm.chutes.ai/v1/chat/completionsThe back-end of the calculation can be switched seamlessly.
This answer comes from the articleChutes: a serverless computing platform for deploying and scaling open source AI modelsThe
May not be reproduced without permission:AI productivity tools " How to quickly deploy and invoke an open source LLM model on Chutes.ai?
English 
简体中文 
日本語 
Deutsch 
Português do Brasil