Providers and ModelsManus

Manus

Manus
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

FieldValue
Model idmanus
Input modalitiesText, Image, Video, Audio, Document
Output modalitiesText, Image, Video, Audio, Document
Context window-
Weight precision-
Featuresautonomous, multi_step, tool_use
Native inferenceNo
NewNo
Supported endpointsPOST /v1/agents/run, GET /v1/agents/{task_id}, GET /v1/agents/{task_id}/messages, POST /v1/agents/{task_id}/stop

Pricing

ChargeSpecRate
Adaptive - Manus 1.6 Liteper task$1.44 - $2.63
Adaptive - Manus 1.6per task$2.89 - $5.25
Adaptive - Manus 1.6 Maxper 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

ParameterTypeRequiredDefaultDescription
inputstringyes-Task description for the agent
task_modeenumno"adaptive"Operating mode for the agent (default | research | coding | etc.). · Allowed: adaptive
agent_profileenumno"manus-1.6"Pre-built agent profile (e.g. analyst, researcher, coder) that tunes the system prompt and tools. · Allowed: manus-1.6, manus-1.6-lite, manus-1.6-max
disable_formattingbooleannofalseSkip the EmpirioLabs Markdown formatting around the Manus agent run. The raw upstream agent output is returned.

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