Quickly run into rate limit

[davids410]

I'm allowed 40,000 tokens per minute through claude 4 opus with my org, but i quickly run into rate limiting. How can i optimize this? Is this more to do with my company's large codebase than my config?

require("avante").setup({
  system_prompt = function()
    local hub = require("mcphub").get_hub_instance()
    return hub and hub:get_active_servers_prompt() or ""
  end,
  custom_tools = function()
    return {
      require("mcphub.extensions.avante").mcp_tool(),
    }
  end,
  provider = "claude",
  providers = {
    claude = {
      model = "claude-opus-4-20250514",
      -- model = "claude-sonnet-4-20250514",
    },
  },
  behaviour = {
    auto_suggestions = false,
    auto_approve_tool_permissions = true,
  },
})