LangChain's model router cuts coding agent cost 64% with no merge-rate loss
hwchase17 · x · 2026-10-14
LangChain added a model router to Open SWE, its open-source coding agent, sending each thread to the cheapest model likely to finish the job.
- A/B test on 973 threads (routed vs always-on GPT-6 Astra): median cost per thread $0.94 vs $2.61 — 64% lower.
- Merged-PR rate: 29.2% routed vs 27.3% on Astra, p-value 0.49 — no significant difference.
- The router sent 56% of threads to the balanced model, 34% to the fast one, 10% to the performance one.
- An always-fast-model variant was killed within a day due to quality complaints from engineers.
Harrison Chase argues the router belongs in the harness, not a gateway, because the harness knows the task. LangChain notes caveats: the control was the most expensive configuration.
More from coding & agent
- Index Network open-sources Social Discovery Protocol: agents negotiate fit on your behalf — carsonfarmer · 2026-10-23
- Installed a formal-verification skill: it silently installed Java, MacBook runs 10 degrees hotter — zealcaiden · 2026-10-23
- OpenAI's Decisions API hits GA: near real-time routing up to 10x faster than GPT-6 Luna — OpenAIDevs · 2026-10-23
- Ruff author warns: upgrade Node/Bun now — --use-system-ca still accepts the eMudhra cert — charliermarsh · 2026-10-23
- Proof of Agent: paste one prompt and your AI mines, grades, and self-governs — adamamcbride · 2026-10-23
- DeepLearning.AI weekly: GPT-6.1 hits 97.9% byte parity on COBOL migration — DeepLearningAI · 2026-10-23