Page cover
For the complete documentation index, see llms.txt. This page is also available as Markdown.

Post Chat Completions

After successfully ensuring that the selected model matches the one chosen when creating Deka LLM in the Deka GPU Service Portal, the next step is to send a request to https://dekallm.cloudeka.ai/v1/chat/completions based on your input. In the Deka LLM API imported into Postman, select Chat Completions.

Completions

In the Authorization tab, select Auth Type: Bearer Token and enter the Secret Key obtained from section Get Secret Key in the Token field.

Authentication

In the {{baseurl}} field, replace it with the Deka LLM API URL https://dekallm.cloudeka.ai/. Then, remove ?model=<string> from the request URL.

Get Model

In the Body tab, select raw.

Tab Body

Copy the following syntax into the raw input field.

Explanation of the syntax.

This field specifies the model to be used. Ensure it matches the model selected as per section Get Model.

This section contains a list of messages in the LLM conversation, providing context to the model by setting its role and including your instructions.

Replace Syntax

Click the Send button to get the response generated by LLM based on your input.

Send Response

You will then receive a response like this.

Response Chat Completions

The response content will be similar to the following.

Last updated