Skip to main content
POST
/
v1
/
flow
/
agents
/
create
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>",
  "user_id": "<string>",
  "team_id": "<string>",
  "created_at": "2023-11-07T05:31:56Z",
  "updated_at": "2023-11-07T05:31:56Z",
  "model_id": "<string>",
  "output": {
    "instructions": "<string>",
    "model_id": "<string>",
    "temperature": 1
  },
  "temperature": 1,
  "planner_temperature": 1,
  "tools": [
    {
      "name": "<string>",
      "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 an agent configuration that defines the model, instructions, reasoning effort, and tools the agent can use. The 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

​
Authorization
string
header
required

Your Seekr API key, sent in the Authorization header with no 'Bearer' prefix.

Body

application/json
​
name
string
required
​
instructions
string
required
​
tools
(CreateFileSearch · object | CreateWebSearch · object | CreateRunPython · object)[] | null
deprecated

DEPRECATED: Use tool_ids instead.

Example:
{
  "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
  }
}
​
tool_ids
string[] | null

Preferred way to associate tools with an agent.

​
model_id
string | null
​
output
AgentOutputConfig · object | null

Optional configuration for the agent's final response. Overrides the top-level settings for response generation.

​
temperature
number | null

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.

Required range: 0 <= x <= 2
​
reasoning_effort
enum<string> | null
default:medium

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.

Available options:
low,
medium,
high,
speed_optimized,
performance_optimized

Response

Successful Response

​
id
string
required
​
name
string
required
​
instructions
string
required
​
status
enum<string>
required
Available options:
Inactive,
Pending,
Active,
Updating,
Failed
​
reasoning_effort
enum<string>
required

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.

Available options:
low,
medium,
high,
speed_optimized,
performance_optimized
​
user_id
string
required
​
team_id
string | null
required
​
created_at
string<date-time>
required
​
updated_at
string<date-time>
required
​
model_id
string | null
​
output
AgentOutputConfig · object | null
​
temperature
number | null
Required range: 0 <= x <= 2
​
planner_temperature
number | null
Required range: 0 <= x <= 2
​
tools
(FileSearch · object | WebSearch · object | RunPython · object | AgentAsTool · object | MCPConnectorTool · object)[]
​
last_deployed_at
string<date-time> | null
​
active_duration
integer
default:0
Required range: x >= 0
Last modified on July 10, 2026