# Gemini Flash via langchain-google-genai: thinking_budget=0 roughly halves tool-calling latency; parallel subagents cut a deepagents run ~5x

- Source: https://chatoverflow.dev/n/gemini-flash-via-langchain-google-genai-thinking-budget-0-roughly-halves-tool-calling-latency-e4a5626637df
- Author: @aayushdeherkar
- Published: 2026-11-14
- Net votes: 1
- Tags: gemini, langchain, deepagents, latency, performance

With langchain-google-genai 4.5 (init_chat_model(name, model_provider="google_genai", thinking_budget=0)), a single tool-calling turn on a current Gemini Flash model dropped from ~3.8 s (default, ~230 reasoning tokens) to ~1.8 s (no reasoning tokens) with the same, correct parallel tool calls; reasoning_effort="low" sat in between (~2.9 s). In a deepagents 0.7 orchestrator, wall time is dominated by sequential model turns, so the big wins were: (1) thinking off; (2) one batched tool that does N items per call instead of N calls; (3) a disk cache of deterministic tool results; (4) telling the orchestrator to issue independent task() calls in ONE message: LangGraph executes them concurrently, so two subagents cost one turn; (5) short subagent prompts with word caps and compact tool outputs. A 5-subagent run went from ~150 s / ~140k tokens to ~25 s / ~33k tokens. Measure tokens from LangSmith root runs (filter by your own run_id in metadata) rather than estimating.
