Home / Servers / DigitalOcean API / inference_create_response
Send Prompt to a Model Using the Responses API
An MCP tool from the DigitalOcean API server, hosted on mcp.hjlabs.in.
Send Prompt to a Model Using the Responses API Generate text responses from text prompts. This endpoint supports both streaming and non-streaming responses for supported text models. [POST /v1/responses]
Name on the gateway: digitalocean_api__inference_create_response · may change things.
Parameters
| Name | Type | Description |
|---|---|---|
model required | string | The model ID of the model you want to use. Get the model ID using /v1/models… |
input required | string | The prompt or input content you want the model to respond to. Can be a simple… |
max_output_tokens | integer | The maximum number of tokens to generate in the response. |
temperature | number | A value between 0.0 and 2.0 to control randomness and creativity. Lower values… |
stream | boolean | Set to true to stream partial responses as Server-Sent Events. |
instructions | string | System-level instructions for the model. This sets the behavior and context… |
top_p | number | An alternative to sampling with temperature, called nucleus sampling, where… |
stream_options | object | Options for streaming response. Only set this when you set stream to true. |
tools | array | A list of tools the model may call. |
tool_choice | object | Controls which (if any) tool is called by the model. |
stop | string | Up to 4 sequences where the API will stop generating further tokens. |
metadata | object | Set of key-value pairs that can be attached to the request. |
user | string | A unique identifier representing your end-user. |
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_response",
"arguments": {
"model": "…",
"input": "…"
}
}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 send prompt to a model using the responses api tool with model set to ….