Together AI chat completion brief
Non-streaming Together AI chat workflow. It sends one explicit question to a selected model, tables returned choices, and summarizes answer quality, finish reason, model, and token usage. It never enables streaming, tool/function calling, file APIs, batches, audio/video APIs, fine-tuning, deployment mutation, or arbitrary Together AI routes.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (6 steps)
completion
?
choices
default
Apply default
choice_count
count
Count items in choices
summarize
?
choice_table
to_table
Format results as a data table
card
to_summary
Format results as a summary card
Settings
Configurable at install. Defaults shown — change them anytime in Recued.
focus
setting
=
Summarize the Together AI answer, model, finish reason, uncertainty, and token usage. Use only the Together AI response.
model
setting
=
MiniMaxAI/MiniMax-M3
question
setting
=
max length
setting
=
800
max tokens
setting
=
900
togetherai
setting
=
temperature
setting
=
0.2
system prompt
setting
=
Answer concisely, call out uncertainty, and avoid inventing facts not present in the prompt.
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.