Basic Information

appmixer.ai.huggingface.SendPrompt

Send Prompt

1.0.0

Public

Send a prompt or a full chat conversation to any model served by Hugging Face Inference Providers and return the generated answer.

Input Ports

in

FieldTypeDescription
Model text Repository ID of a chat model on the Hub, e.g. meta-llama/Llama-3.1-8B-Instruct. Append a routing suffix to choose the provider: :fastest (default), :cheapest, :preferred, or a provider name such as openai/gpt-oss-120b:groq.
Prompt textarea The user message to send. Ignored when Messages is filled in.
System Prompt textarea Optional instructions that steer the model, e.g. You are a concise assistant.
Messages textarea Optional full conversation as a JSON array, e.g. [{"role": "user", "content": "Hi"}]. Overrides Prompt when set.
Max Tokens number Maximum number of tokens to generate. Leave empty for the provider default.
Temperature number Sampling temperature between 0 and 2. Lower is more deterministic.
Top P number Nucleus sampling probability mass between 0 and 1.

Output Ports

out

FieldTypeDescription
Completion ID string -
Model string -
Answer string -
Finish Reason string -
Prompt Tokens integer -
Completion Tokens integer -
Total Tokens integer -

Full Metadata