Actions16
- LLM (Text Generation) Actions
- Image Generation Actions
- Video Generation Actions
- Text-to-Speech Actions
- Speech-to-Text Actions
- Music Generation Actions
- Embeddings Actions
- Content Moderation Actions
- Custom Inference Actions
Custom Inference → Get Status
AI-generatedSummary
Retrieve the current status of a custom inference job on a specified chute by providing the job ID.
Inputs
- Chute — Select a specific chute URL to query for the inference job status. Defaults to 'https://llm.chutes.ai'.
- Job ID (required) — Specify the unique ID of the inference job whose status you want to check.
- Additional Options — Optionally configure timeout in seconds (maximum wait time), provide a webhook URL to receive async results, set the job priority (low, normal, high), and choose the output format (JSON or raw).
Output shape
a single record
Returns the inference job status as a JSON object from the chute's /v1/inference/jobs/{jobId} endpoint. If a timeout is specified and exceeded, the node throws an error and can trigger a retry workflow. The output format can be JSON or raw as per user option.
Examples
Example 1: Check inference job status by job ID on default chute
Set the Job ID input to the ID of the inference job to check; optionally select a different chute URL; leave other options default or empty. Execute node to receive the current status data.