Manus | EmpirioLabs AI Docs

Manus · Tools & Agents

POST /v1/agents/run

Autonomous AI agent that turns a high-level prompt into subtasks, calls tools and APIs, and delivers end-to-end results without manual orchestration.

At a glance

Field	Value
Model id	`manus`
Model release date	-
Input modalities	Text, Image, Video, Audio, Document
Output modalities	Text, Image, Video, Audio, Document
Context window	-
Weight precision	-
Features	autonomous, multi_step, tool_use
Native inference	No
New	No
Supported endpoints	`POST /v1/agents/run`, `GET /v1/agents/{task_id}`, `GET /v1/agents/{task_id}/messages`, `POST /v1/agents/{task_id}/stop`

Pricing

Charge	Spec	Rate
Lite profile	per task	$1.44 - $2.63
Standard profile	per task	$2.89 - $5.25
Max profile	per task	$5.25 - $9.19

Example request

curl https://api.empiriolabs.ai/v1/agents/run \
  -H 'Authorization: Bearer $EMPIRIOLABS_API_KEY' \
  -H 'Content-Type: application/json' \
  -d '{"model": "manus", "input": "Find the cheapest flight from NYC to LAX next week"}'

Parameters

Parameter	Type	Required	Default	Description
`input`	string	yes	-	Task description for the agent
`attachments`	array	no	-	Files for the agent to work with (any type: audio, video, images, documents, data). Each item is a URL string or an object with url, filename, and mime_type. Files are placed in the agent’s workspace before the task starts. Up to 10 files per message.
`agent_profile`	enum	no	`"standard"`	Capability profile for the task: `standard` for most work, `lite` for quicker, lower-cost tasks, or `max` for the most complex work. A follow-up sent with `task_id` can switch profiles. · Allowed: `standard`, `lite`, `max`
`disable_formatting`	boolean	no	false	Return the agent’s output without added Markdown formatting. Applies to streamed runs only.

Machine-readable schema: GET https://api.empiriolabs.ai/v1/models/manus.