Chat - Response - AGCloud API

Authorization

Auth Type: Bearer Auth (In: header)
Format: Authorization: Bearer <YOUR_API_KEY>
Description: Use Bearer <YOUR_API_KEY>. Format: Authorization: Bearer sk-xxxxxx.
API Key: where API Key is your AGCloud API KEY

Field	Type	Required	Range	Description
`model`	`string`	✅	-	The model ID
`input`	`string \| array<object>`	✅	-	Input content for the model.
`>input.role`	`string`	✅	`user` `assistant` `system` `developer`	The role of the message input. One of user, assistant, system, or developer.
`>input.content`	`string \| array`	✅	-	A text input to the model when string; a list of one or many input items to the model, containing different content types when array.

{
  "role": "user",
  "content": [
    {
      "type": "input_text",
      "text": "Who are you?"
    }
  ]
}

Field	Type	Required	Range	Description
`type`	`string`	✅	-	The type of content block. Supported: `input_text`, `input_image`, `input_file`.
`text`	`string`	-	`input_text`	The text content of the input.
`image_url`	`string`	-	`input_image`	The URL of the image to send to the model.
`filename`	`string`	-	`input_file`	The name of the file being uploaded.
`file_url`	`string`	-	`input_file`	The URL of the file to send to the model.

Field	Type	Required	Range	Description
`instructions`	`string`	-	-	System instructions that the model should follow when generating a response.
`max_output_tokens`	`integer`	-	-	The maximum number of tokens the model can generate in the response.
`temperature`	`number`	-	`0.0` - `2.0`	Controls the randomness of the output. Lower values produce more focused responses, higher values produce more creative outputs.
`top_p`	`number`	-	`0.0` - `1.0`	Nucleus sampling parameter. The model considers tokens with top_p cumulative probability mass.
`stream`	`boolean`	-	-	If `true`, returns a stream of server-sent events (SSE) as the response is generated.
`tools`	`array<object>`	-	-	A list of tools the model may call. Use this to provide functions the model can generate JSON inputs for.
`tool_choice`	`string \| object`	-	-	Controls which tool is called. `none`: no tool, `auto`: model decides, `required`: must call a tool.
`reasoning`	`object`	-	-	Configuration for reasoning effort. Controls how much reasoning the model performs before generating a response.
`previous_response_id`	`string`	-	-	The ID of a previous response to use as context for multi-turn conversations.
`truncation`	`string`	-	`auto` \| `disabled`	Truncation strategy. `auto`: automatically truncates input to fit context window; `disabled`: returns an error if input exceeds context window.