Groq Responses API generation brief
Groq Responses API workflow. It creates one bounded non-streaming text response, tables output items, and summarizes response status, generated content, reasoning metadata, and token usage. It never enables tools, tool_choice, parallel tool calls, streaming, storage, metadata, previous responses, audio, files, or arbitrary Groq routes.
How it works
Inspect the data fetches, transforms, gates, and output this recipe runs.
Process (6 steps)
response
?
output_items
default
Apply default
output_count
count
Count items in output items
summarize
?
output_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.
groq
setting
=
focus
setting
=
Summarize the Groq Responses API output, response status, generated message content, reasoning metadata, usage, and any incomplete or error details.
model
setting
=
openai/gpt-oss-120b
prompt
setting
=
max length
setting
=
800
temperature
setting
=
0.2
instructions
setting
=
Produce a concise, directly usable response. State assumptions and avoid unsupported claims.
reasoning effort
setting
=
medium
max output tokens
setting
=
900
Trust & control
What installing this recipe would let it do. Recued grants these permissions at install — review them there before approving.