Submit a GPU workload to Jungle Grid. Returns a job_id immediately — the job runs asynchronously. Supports environment variables for runtime configuration or env-backed code payloads when the command would be too long. After submitting, prefer stream_job_logs for real-time output, then use get_job or get_job_logs for final status and logs. Managed jobs automatically upload regular files written under /workspace/artifacts as Jungle Grid artifacts. Use estimate_job first if you want a cost estimate before committing.

Get the current status and full detail of a Jungle Grid job by its ID. Poll this after submit_job to track progress. Terminal statuses are 'completed', 'failed', and 'cancelled'.

List recent Jungle Grid jobs for the authenticated user, newest first.

Cancel a pending, queued, or running Jungle Grid job. Has no effect on already-terminal jobs.

Retrieve the stdout and stderr output of a completed or running Jungle Grid job. Call this after get_job reports status 'completed' or 'failed'.

List managed result artifacts uploaded by a Jungle Grid job. For managed jobs, Jungle Grid automatically uploads regular files written under /workspace/artifacts.

Create a temporary signed download URL for a managed job artifact.

Estimate the credit cost and GPU tier for a job before submitting it. Use this to check affordability or compare optimize_for options before calling submit_job.

Stream live log output for a running or recently completed job. Blocks until the job reaches a terminal state (completed/failed/cancelled) or 10 minutes elapses. Returns the full stdout and stderr accumulated during the run. Prefer this over get_job_logs for jobs that are actively running or when you want a real-time execution view.