Home / Servers / DigitalOcean API / inference_create_batch
Create a Batch Inference Job
An MCP tool from the DigitalOcean API server, hosted on mcp.hjlabs.in.
Create a Batch Inference Job Submits a batch job against a previously uploaded JSONL input file. The upload must have completed before this call; otherwise the request is rejected. Supply a unique request_id to make the… [POST /v1/batches]
Name on the gateway: digitalocean_api__inference_create_batch · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
file_id required | string | The file_id returned by POST /v1/batches/files. |
provider required | openai | anthropic | The inference provider whose JSONL schema the input file conforms to. openai… |
endpoint | /v1/responses | /v1/chat/completions | Inference endpoint each request is dispatched to. **Required when provider is… |
completion_window required | 24h | Time window in which the job must complete. Jobs that do not finish in time… |
request_id required | string | Client-supplied idempotency key. Retries with the same value return the… |
metadata | object | Optional string-valued metadata to attach to the job. |
How to call it
Through the Smart Gateway, any client can run it by name with call_tool, or let the gateway find it with search_tools:
{
"name": "digitalocean_api__inference_create_batch",
"arguments": {
"file_id": "…",
"provider": "…",
"completion_window": "…",
"request_id": "…"
}
}Or connect the DigitalOcean API server directly, which lists 874 tools including this one:
claude mcp add --transport http hj-digitalocean-api https://mcp.hjlabs.in/mcp/digitalocean-api \
--header "Authorization: Bearer YOUR_API_KEY"Try asking
Use the create a batch inference job tool with file_id set to ….