Skip to main content
truss model-logs [OPTIONS]
Fetches logs for a deployed model. Use this command to debug issues or monitor model behavior in production.

​
Options

​
--remote
TEXT
Name of the remote in .trussrc.
​
--model-id
TEXT
ID of the model.
​
--deployment-id
TEXT
ID of the deployment.
​
--tail
Tail for ongoing logs. Streams new log entries as they arrive.
​
--start
DATETIME
Start of the log time range (ISO 8601). No-timezone values are local. Defaults to a short look-back ending at —end. Window must be <= 7 days.
​
--end
DATETIME
End of the log time range (ISO 8601). No-timezone values are local. Defaults to now. Window must be <= 7 days.
​
--since
TEXT
Logs from a relative time ago until now, written as a number plus a unit of s, m, h, or d (for example 90s, 2h, or 3d). Max 7d. Cannot be combined with --start or --end.
​
--min-level
debug | info | warning | error
Minimum log severity. Defaults to all lines. Any value returns lines at or above that severity and drops lines with no level.
​
--includes
TEXT
Case-sensitive substring that must appear in the message (repeatable).
​
--excludes
TEXT
Case-sensitive substring that drops any line containing it (repeatable).
​
--search-pattern
TEXT
RE2 regex matched against the message. Prefer —includes/—excludes.
​
--replica
TEXT
Only return logs emitted by this replica (5-char short ID).
​
--request-id
TEXT
Only return logs tagged with this inference request ID.
​
--log
humanfriendly | W | WARNING | I | INFO | D | DEBUG
default:"humanfriendly"
Logging verbosity. humanfriendly (default) is pretty-printed; INFO, DEBUG, WARNING produce structured logs.
​
--non-interactive
Disable interactive prompts. Use in CI/automated contexts where stdin isn’t a TTY.
Example: Fetch logs for a specific deployment: 
truss model-logs --model-id YOUR_MODEL_ID --deployment-id YOUR_DEPLOYMENT_ID
Stream logs in real-time: 
truss model-logs --model-id YOUR_MODEL_ID --deployment-id YOUR_DEPLOYMENT_ID --tail
Fetch logs from the last two hours: 
truss model-logs --model-id YOUR_MODEL_ID --deployment-id YOUR_DEPLOYMENT_ID --since 2h
Fetch logs for a specific time window: 
truss model-logs --model-id YOUR_MODEL_ID --deployment-id YOUR_DEPLOYMENT_ID --start 2026-06-01T00:00:00 --end 2026-06-01T01:00:00
Filter logs to errors only: 
truss model-logs --model-id YOUR_MODEL_ID --deployment-id YOUR_DEPLOYMENT_ID --min-level error

​
Rate limits

Baseten limits the deployment logs endpoint (POST /v1/models/{model_id}/deployments/{deployment_id}/logs) to 30 requests/second per API key. Interactive use, including --tail, stays well under that limit. Scripts that wrap truss model-logs in a tight poll loop can hit the limit and receive 429 Too Many Requests. Wait for the response’s retry_after value (in seconds) before retrying. For the full response shape and a retry example, see management API rate limits.