curl --request POST \
--url https://flow.seekr.com/v1/flow/agents/create \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "My Agent",
"instructions": "You are a helpful assistant that can search files, browse the web, and run Python code.",
"model_id": "deployment-123",
"temperature": 0.4,
"reasoning_effort": "medium",
"tool_ids": [
"tool-123",
"tool-456"
]
}
'{
"id": "<string>",
"name": "<string>",
"instructions": "<string>",
"status": "Inactive",
"reasoning_effort": "low",
"user_id": "<string>",
"team_id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"model_id": "<string>",
"planner_model_id": "<string>",
"tool_model_id": "<string>",
"output": {
"frequency": "always",
"instructions": "<string>",
"model_id": "<string>",
"temperature": 1
},
"temperature": 1,
"planner_temperature": 1,
"tools": [
{
"name": "file_search",
"tool_env": {
"FILE_SEARCH_INDEX": "<string>",
"DOCUMENT_TOOL_DESC": "<string>",
"EMBEDDING_MODEL": "<string>",
"TOP_K": 10,
"SCORE_THRESHOLD": 0
},
"id": "<string>"
}
],
"last_deployed_at": "2023-11-07T05:31:56Z",
"active_duration": 0
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}Create agent v1
Create a new agent with a model, instructions, and optional tools.
curl --request POST \
--url https://flow.seekr.com/v1/flow/agents/create \
--header 'Authorization: <api-key>' \
--header 'Content-Type: application/json' \
--data '
{
"name": "My Agent",
"instructions": "You are a helpful assistant that can search files, browse the web, and run Python code.",
"model_id": "deployment-123",
"temperature": 0.4,
"reasoning_effort": "medium",
"tool_ids": [
"tool-123",
"tool-456"
]
}
'{
"id": "<string>",
"name": "<string>",
"instructions": "<string>",
"status": "Inactive",
"reasoning_effort": "low",
"user_id": "<string>",
"team_id": "<string>",
"created_at": "2023-11-07T05:31:56Z",
"updated_at": "2023-11-07T05:31:56Z",
"model_id": "<string>",
"planner_model_id": "<string>",
"tool_model_id": "<string>",
"output": {
"frequency": "always",
"instructions": "<string>",
"model_id": "<string>",
"temperature": 1
},
"temperature": 1,
"planner_temperature": 1,
"tools": [
{
"name": "file_search",
"tool_env": {
"FILE_SEARCH_INDEX": "<string>",
"DOCUMENT_TOOL_DESC": "<string>",
"EMBEDDING_MODEL": "<string>",
"TOP_K": 10,
"SCORE_THRESHOLD": 0
},
"id": "<string>"
}
],
"last_deployed_at": "2023-11-07T05:31:56Z",
"active_duration": 0
}{
"detail": [
{
"loc": [
"<string>"
],
"msg": "<string>",
"type": "<string>",
"input": "<unknown>",
"ctx": {}
}
]
}POST /v2/flow/agents/create instead of this deprecated endpoint.tool_ids parameter accepts IDs for any tool type, including agent-as-tools. When including agent-as-tools, the sub-agents and their tool wrappers must already exist before creating the supervisor agent.
For details on building multi-agent workflows, see Agent as tool.Authorizations
Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.
Body
Name of the agent.
256Instructions that tell the agent how to behave.
32768Deprecated. Use tool_ids instead.
- CreateFileSearch
- CreateWebSearch
- CreateRunPython
Show child attributes
Show child attributes
{
"name": "file_search",
"tool_env": {
"document_tool_desc": "Search through uploaded documents",
"file_search_index": "my-document-index",
"score_threshold": 0.7,
"top_k": 10
}
}
IDs of the tools the agent can use. Use this field instead of tools.
32768ID of the model the agent uses to respond.
32768ID of the model the agent uses to plan its work.
32768ID of the model the agent uses when it calls tools.
32768Optional configuration for the agent's final response. Overrides the top-level settings for response generation.
Show child attributes
Show child attributes
Controls the predictability of the agent's reasoning. Accepts a value from 0 to 2. Defaults to 0.6. Lower values produce more consistent results, and higher values introduce more variation.
0 <= x <= 2Controls how much reasoning the agent uses when it works through a request.
low, medium, high, speed_optimized, performance_optimized Response
Resource created
ID of the agent.
Name of the agent.
Instructions that tell the agent how to behave.
Inactive, Pending, Active, Updating, Failed Controls how much reasoning the agent uses when working through a request. Accepts low, medium, or high, where higher levels produce more thorough reasoning. The speed_optimized and performance_optimized values are only supported for backward compatibility. speed_optimized maps to low, and performance_optimized maps to high.
low, medium, high, speed_optimized, performance_optimized ID of the user who owns the agent.
ID of the team the agent belongs to.
Time the agent was created, in ISO 8601 format.
Time the agent was last updated, in ISO 8601 format.
ID of the model the agent uses to respond.
ID of the model the agent uses to plan its work.
ID of the model the agent uses when it calls tools.
Optional configuration for the agent's final response. Overrides the top-level settings for response generation.
Show child attributes
Show child attributes
Controls the predictability of the agent's reasoning. Accepts a value from 0 to 2. Defaults to 0.6. Lower values produce more consistent results, and higher values introduce more variation.
0 <= x <= 2Controls the predictability of the agent's planning. Lower values produce more consistent plans, and higher values introduce more variation.
0 <= x <= 2Tools the agent can use.
- FileSearch
- WebSearch
- RunPython
- AgentAsTool
- MCPConnectorTool
Show child attributes
Show child attributes
Time the agent was last deployed, in ISO 8601 format.
x >= 0