LangChain Reference home page

GitHub
Main Docs

Overview
Agent
Middleware
Backends
Sandboxes
Subagents

Deep Agents Code

⌘I

Chat LangChain

What can I help with?

Enter to send·Shift+Enter new line

Menu

Overview Agent Middleware Backends Sandboxes Subagents

Deep Agents Code

Language

Theme

Pythondeepagentsprofilesharness_nvidia_nemotron_3_ultraModelRateLimitRetryMiddlewarewrap_model_call

Method●Since v0.7

wrap_model_call

Copy

wrap_model_call(
  self,
  request: ModelRequest[Any],
  handler: Callable[[ModelRequest[Any

Used in Docs

Build customer support with handoffs
CopilotKit
Custom middleware
Handoffs
Models

View source on GitHub

]

]

,

ModelCallResult

]

)

->

ModelCallResult

Retry rate-limit failures with a short backoff.