feat: add service_tier to openai langchain chat

[SamuelScheit]

OpenAI introduced Flex processing which

provides significantly lower costs for Chat Completions or Responses requests in exchange for slower response times and occasional resource unavailability. It is ideal for non-production or lower-priority tasks such as model evaluations, data enrichment, or asynchronous workloads.

The python counterpart already has the ability to specify a service_tier but the JS library is missing it, which this PR adds

Example

const llm = new ChatOpenAI({
	model: "o4-mini",
	apiKey: process.env.OPENAI_API_KEY,
	service_tier: "flex",
	timeout: 60 * 1000 * 30,
});

llm.invoke("Hi", {
	service_tier: "default", // service_tier can be overridden when invoking llm
});

Keep in mind that:

Flex processing is in beta, and currently only available for o3 and o4-mini models.

[vercel]

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name	Status	Preview	Comments	Updated (UTC)
langchainjs-docs	✅ Ready (Inspect)	Visit Preview		Jun 8, 2025 0:35am

1 Skipped Deployment

Name	Status	Preview	Comments	Updated (UTC)
langchainjs-api-refs	⬜️ Ignored (Inspect)			Jun 8, 2025 0:35am