Skip to main content
Use ai-stats:subagent when the main model should hand off a self-contained task to a smaller or faster worker model during the same request. The main model calls the Subagent tool with a task description. AI Stats runs the worker model server-side, returns the worker result as tool context, and lets the main model finish the answer.

​
Quick start

curl https://api.phaseo.app/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "openai/gpt-5-nano",
    "messages": [
      { "role": "user", "content": "Compare these release notes and summarize the breaking changes." }
    ],
    "tools": [
      {
        "type": "ai-stats:subagent",
        "parameters": {
          "model": "openai/gpt-5-nano",
          "instructions": "Return concise findings for the main model. Do not address the end user directly.",
          "max_uses": 3,
          "max_completion_tokens": 1200
        }
      }
    ]
  }'

​
Parameters

{
  "type": "ai-stats:subagent",
  "parameters": {
    "model": "openai/gpt-5-nano",
    "instructions": "You are a fast, focused worker. Complete only the delegated task.",
    "max_uses": 3,
    "max_completion_tokens": 1200,
    "reasoning": { "effort": "low" },
    "temperature": 0.2
  }
}
ParameterTypeDefaultDescription
modelstringopenai/gpt-5-nanoWorker model to call.
instructionsstringfocused worker instructionsExtra instructions appended to the default Subagent behavior.
max_usesinteger10Maximum Subagent calls during the server-tool loop.
max_completion_tokensintegerAdvisor defaultMax output tokens for each worker response.
max_tokensintegerAdvisor defaultLegacy alias for max_completion_tokens.
reasoningobjectprovider defaultReasoning config forwarded to the worker call when supported.
temperaturenumberprovider defaultSampling temperature for the worker call.

​
Tool-call arguments

The model normally calls Subagent with task_description: 
{
  "task_description": "Extract the three highest-risk migration steps from the supplied plan."
}
AI Stats also accepts task, prompt, or input as aliases when a model emits a slightly different argument name.

​
What the tool returns

Subagent returns JSON as the tool result: 
{
  "status": "ok",
  "model": "openai/gpt-5-nano",
  "result": "The highest-risk steps are schema migration, traffic cutover, and rollback verification."
}
If the worker request cannot run, AI Stats returns a tool error such as subagent_invalid_request, subagent_max_uses_exceeded, or subagent_request_failed.

​
Usage and pricing

Subagent calls increment: 
{
  "usage": {
    "server_tool_use": {
      "subagent_requests": 1
    }
  }
}
The worker model’s tokens are included in total usage and can be priced at the selected worker model’s rates.
Last modified on July 2, 2026