Send Request - Modellss Docs

You can paste the following command into your terminal to execute your first API request. Ensure that you replace YOUR_API_KEY with the token you generated in the Modelless Hub dashboard (sk-xxx).

This request queries the model to complete the text starting with the prompt “Say this is a test gpt-3.5-turbo”. You should receive a response similar to the following:


1 {
2    "id":"chatcmpl-abc123",
3    "object":"chat.completion",
4    "created":1677858242,
5    "model":"gpt-3.5-turbo-0301",
6    "usage":{
7       "prompt_tokens":13,
8       "completion_tokens":7,
9       "total_tokens":20
10    },
11    "choices":[
12       {
13          "message":{
14             "role":"assistant",
15             "content":"\n\nThis is a test!"
16          },
17          "finish_reason":"stop",
18          "index":0
19       }
20    ]
21 }

You have now generated your first chat completion. We observe that finish_reason is stop, indicating that the API has returned a complete output generated by the model. In the previous request, we generated only one message, but you can set the n parameter to generate multiple message options. In this example, gpt-3.5-turbo is primarily used for traditional text completion tasks. The model is also optimized for chat applications.