Body
Parameters for creating a chat completion.
The model name to use.
"llama3.2:1b"
List of messages that form the conversation.
Sampling temperature, between 0 and 2.
0.7
Alternative sampling parameter using nucleus sampling.
1
Number of completions to generate.
1
If true, returns streaming response chunks.
true
Sequences where the API will stop generating further tokens.
The maximum number of tokens to generate in the completion.
256
A value between -2.0 and 2.0 that influences the presence of new topics.
0
A value between -2.0 and 2.0 that penalizes token repetition.
0
Adjusts the probabilities of specific tokens.
A unique identifier for the end-user.
Response
Chat completion generated successfully. The response format varies depending on the stream parameter.
Unique identifier for the completion.
"chatcmpl-856"
Type of the returned object.
"chat.completion"
Timestamp of the completion creation.
1738865830
The model used to generate the completion.
"llama3.1:8b"
System fingerprint of the completion.
"fp_ollama"
List of generated completions.
Information about token usage.