Model Comparison
🤖 AI Drafted (Not reviewed)
Compare responses from multiple LLM models
|
|
| Tool id |
model_comparison |
| Category |
llm |
| Uses a language model |
yes |
| Needs a generative model |
no |
| Runs over many items |
no |
| Item handling |
batch |
| Structured output |
no |
| Human-verified |
not yet |
What it reads
| Port |
Type |
Required |
What it is |
Prompt (prompt) |
text |
yes |
Prompt to send to all models |
System Prompt (system_prompt) |
text |
no |
Optional system prompt |
What it emits
| Port |
Type |
Required |
What it is |
Results (results) |
json |
— |
Comparison results from all models |
Fastest Response (fastest) |
text |
— |
Response from fastest model |
Cheapest Response (cheapest) |
text |
— |
Response from cheapest model |
Summary (summary) |
json |
— |
Summary statistics |
Options
| Option |
Type |
Default |
What it does |
models |
array |
[] |
Models to compare. Empty = the workflow’s own default provider/model (tier aliases like $medium resolve through AI Defaults, #4325). |
timeout_seconds |
integer |
60 |
Timeout per model in seconds. |
The prompt it sends
This tool does not send a prompt — it does its work in code.