Skip to main content
Inspect inference requests and responses captured by Catalyst observability. View recent inferences, filter by model, and drill into the full request and response payloads. Alias: inf inferences

​
List Inferences

Display recent inferences in the active project. 
inf inference list
Alias: inf inference ls

​
Options

FlagDescriptionDefault
-l, --limit <n>Maximum number of results20
-m, --model <model>Filter by model nameAll models
--task <taskId>Filter by task ID—
--cursor <cursor>Pagination cursor (from a previous response)—
# List the 10 most recent inferences
inf inference list --limit 10

# Filter by model
inf inference list --model meta-llama/llama-3.1-8b-instruct/fp-8
The output table shows the inference ID, model, status code (color-coded), input/output token counts, latency in milliseconds, cost, and timestamp. When more results are available, the CLI displays a pagination cursor you can pass to the next call with --cursor.

​
Get Inference Details

View the full request and response for a specific inference. 
inf inference get <id>

​
Arguments

ArgumentRequiredDescription
idYesThe inference ID
Displays the complete request (method, path, and body as formatted JSON) and the full response body as formatted JSON. This is useful for debugging specific API calls or inspecting model behavior. 
inf inference get inf_abc123def456