Intel / article

📦 Try Out Kimi K3 in LangSmith LLM Gateway Run agents with Kimi 3 using just yo

Source: docs.langchain.com
Author: LangChain
Date: Published Aug 6, 2026

Context

LangChain's beta Gateway Credits let an eligible LangSmith workspace call hosted models, including Moonshot AI's Kimi K3, using its LangSmith API key instead of setting up a separate model-provider account. The documentation explains that the requested model identifier determines whether a call spends Gateway Credits or uses a separately configured provider's credentials.

This consolidates access and spending controls for hosted-model calls. Existing organization, workspace, key and user spending caps also apply to Gateway Credits. The documented prerequisites include a qualifying paid plan and a workspace-scoped key with the necessary permissions, so possession of an arbitrary LangSmith key is insufficient.

Terms in this piece · Glossary

LLM — A large language model — the neural network behind tools like Claude and ChatGPT, trained on huge amounts of text to predict what comes next.

Key quotes

“Gateway Credits let you call LangChain-hosted models through the standard LLM Gateway API without setting up a provider account or key.”
LangChain

“Gateway Credits are denominated in LangChain Credit Units (LCUs) at $1.50 per LCU ; each call consumes LCUs based on token usage.”
LangChain

“Standard gateway spend policies apply to hosted-model traffic, so any organization, workspace, API key, or user cap you have configured also governs Gateway Credit usage.”
LangChain

Read the source docs.langchain.com