Skip to content
Recued
Menu
← Back to recipes

Together AI chat completion brief

by recued-core v1

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 6 steps

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 8 configurable

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.

Where it runs

Device + server Runs on your device (browser) or your server.

Permissions it requires

Read your Togetherai connection
Declared by the recipe — Recued grants these at install, where you review them before approving.

About

Tags

togetherai togetheraichatllmopen-modelsanswer-reviewai-summarypack:togetherai

Details

6 steps 8 configurable settings recipe_id: togetherai-chat-completion-brief