Basic Information

appmixer.ai.requesty.SendPrompt

Send Prompt

1.0.0

Public

Sends a prompt to a model routed through Requesty and returns the answer.

Input Ports

in

FieldTypeDescription
Prompt textarea The text input that the model will use to generate a response.
Instructions textarea The system instructions that the assistant uses. For example 'Be precise and concise.'
Model text The provider-prefixed model identifier to use (for example openai/gpt-4o or anthropic/claude-3-5-sonnet-latest). The list is populated from your account's available models.
Temperature number Controls the randomness of the model. Lower values make the output more focused and deterministic, higher values more creative. Typically between 0 and 2.
Max Tokens number The maximum number of completion tokens returned by the API. The total length of input tokens and generated tokens is limited by the model's context length.
Top P number An alternative to sampling with temperature, called nucleus sampling, valued between 0 and 1. We generally recommend altering this or temperature but not both.
Frequency Penalty number Number between -2.0 and 2.0. Positive values penalize new tokens based on their existing frequency in the text so far, decreasing the model's likelihood to repeat the same line verbatim.
Presence Penalty number Number between -2.0 and 2.0. Positive values penalize new tokens based on whether they appear in the text so far, increasing the model's likelihood to talk about new topics.

Output Ports

out

FieldTypeDescription
Answer -
Prompt -
Finish Reason -
ID -
Model -
Created Timestamp -
Prompt Tokens -
Completion Tokens -
Total Tokens -

Full Metadata