---
format: "aidr-story-markdown/v1"
id: "1f9d81285bbf93f0bd1efc2ddc861b2c10ecb236794aa0d86d6ba2fff4446798"
canonical_url: "https://aidr.today/1f9d8128?lang=en"
title: "LangChain Launches LangSmith Fine Tuning to Cut Model Latency"
lang: "en"
requested_lang: "en"
available_langs: ["en","vi"]
translation_fallback: null
fallback_fields: []
published_at: "2026-09-24T20:39:46.000Z"
category: "Products"
topics: ["openai","langchain","fine-tuning","open-source","rag","agent","multi-agent","harness"]
source_urls: ["https://marketbrief.now/ai/langchain-launches-langsmith-fine-tuning-to-cut-model-latency-63fbc6ca","https://huggingnews.com/ai/langchain-launches-langsmith-fine-tuning-to-cut-model-latency-63fbc6ca","https://huggingnews.com/ai/langchain-launches-managed-deep-agents-08-and-langsmith-fine-tuning-fbb89809","https://marketbrief.now/ai/langchain-launches-managed-deep-agents-08-and-langsmith-fine-tuning-fbb89809"]
summary: "The newly released smithtune tool enables the conversion of tracing data into training datasets for custom AI models. Currently in public beta, this open-source command-line interface integrates with the LangSmith platform to automate the entire lifecycle of training specialized models, which LangChain says will lower operational expenses and reduce inference latency. The release includes partnerships with Baseten and Fireworks AI to provide the necessary infrastructure for training and deployment. Baseten allows developers to deploy model checkpoints with a single command, while Fireworks AI provides managed supervised fine-tuning and evaluation capabilities through the smithtune CLI."
---

# LangChain Launches LangSmith Fine Tuning to Cut Model Latency

> [Open the canonical story](<https://aidr.today/1f9d8128?lang=en>)

**Published:** 2026-09-24T20:39:46.000Z
**Category:** Products
**Topics:** openai, langchain, fine\-tuning, open\-source, rag, agent, multi\-agent, harness

## Summary

The newly released smithtune tool enables the conversion of tracing data into training datasets for custom AI models\. Currently in public beta, this open\-source command\-line interface integrates with the LangSmith platform to automate the entire lifecycle of training specialized models, which LangChain says will lower operational expenses and reduce inference latency\. The release includes partnerships with Baseten and Fireworks AI to provide the necessary infrastructure for training and deployment\. Baseten allows developers to deploy model checkpoints with a single command, while Fireworks AI provides managed supervised fine\-tuning and evaluation capabilities through the smithtune CLI\.

## Sources

- [Story source](<https://marketbrief.now/ai/langchain-launches-langsmith-fine-tuning-to-cut-model-latency-63fbc6ca>)
- [Story source](<https://huggingnews.com/ai/langchain-launches-langsmith-fine-tuning-to-cut-model-latency-63fbc6ca>)
- [Story source](<https://huggingnews.com/ai/langchain-launches-managed-deep-agents-08-and-langsmith-fine-tuning-fbb89809>)
- [Story source](<https://marketbrief.now/ai/langchain-launches-managed-deep-agents-08-and-langsmith-fine-tuning-fbb89809>)