Get generation
get_generationRead a generation's status, outputs, or failure details. Completed results include all output files in provider order.
Tool call template
Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.
{
"id": 1,
"jsonrpc": "2.0",
"method": "tools/call",
"params": {
"arguments": {
"id": "<id>"
},
"name": "get_generation"
}
}Input Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Generation ID returned by a generation tool. | |
| wait | No | Wait for completion or failure. A timeout leaves generation running. Defaults to false, which returns the current status immediately. | |
| timeout | No | How long to wait for this generation when wait is true, in seconds. Defaults to and is capped at 45 seconds. Timing out leaves the generation running. | |
| llm_model | No | The model identifier you are running as, for example "claude-opus-4-8" or "gpt-5.2". Omit it or pass "unknown" if you are not certain; the tool runs the same either way. Recorded only for the server developer's analytics. | |
| inline_media | No | Set to false to get only the JSON and resource links, without images or audio, for example when re-reading a result you have already seen. Defaults to true, which adds images and audio after their links while the result stays within its size limit. |
Output Schema
| Name | Required | Description | Default |
|---|---|---|---|
| id | Yes | Generation ID. Pass it as id to get_generation. | |
| type | Yes | Requested output type: image, video, audio, or svg. | |
| model | Yes | Model ID the generation used. | |
| status | Yes | Current generation status. | |
| failure | Yes | Failure details, or null when generation has not failed. | |
| outputs | Yes | Output files in provider order. Empty until the generation completes. | |
| created_at | Yes | Time the generation was created. | |
| brand_session_id | Yes | Brand the generation belongs to. | |
| message_for_assistant | No | Context, explanations, or actionable guidance for the calling assistant. Hosts may display it, but it is not copy that must be shown to the user verbatim. |