Mistral chat completion brief
Read-only Mistral chat completion workflow. It reads model metadata, sends explicit non-streaming messages through recued-core.mistral.chat_completion.create, and summarizes the response and token usage. It never enables tools, connector tools, streaming, file upload/download, agent mutation, workflow execution, fine-tuning mutation, or arbitrary Mistral API routes.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (7 steps)
model_details
?
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 Mistral response, finish reasons, and token usage. Call out any practical prompt/model follow-ups visible in the response. Do not invent facts outside the Mistral API response.
model
setting
=
mistral-small-latest
mistral
setting
=
messages
setting
=
max length
setting
=
900
max tokens
setting
=
512
safe prompt
setting
=
false
temperature
setting
=
0.2
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.