feat(@langchain/google) Support Flex and Priority tiers

[afirstenberg]

Privileged issue

• I am a LangChain maintainer, or was asked directly by a LangChain maintainer to create an issue here.

Issue Content

https://blog.google/innovation-and-ai/technology/developers-tools/introducing-flex-and-priority-inference/

Possibly just the AI Studio API, but this allows cost savings or priority access for a fee.

Mostly configuration parameter changes (so likely in the discovery doc), but it does have a header in the reply with the service tier actually used.

Is there a standard way to pass this along so LangSmith can handle the billing estimate accordingly?

(Hunter Lovell (@hntrl) Christian Bromann (@christian-bromann))

[afirstenberg]

See also #10482 and #10491 for how this needs to be done on Vertex

[saalihou]

For anyone looking for a patch solution while this is getting implemented, just extend the ChatGoogle class like below and use this class instead:

/**
 * Extends ChatGoogle to inject the `service_tier` parameter into the request body.
 * LangChain doesn't support this yet, but it's a top-level field in the Gemini API
 * alongside generationConfig/contents. Since _generate spreads invocationParams()
 * into the body, we can sneak it in here.
 * Values: 'standard' (default), 'priority' (low-latency, ~75-100% premium), 'flex' (50% discount, sheddable)
 */
class ChatGoogleWithServiceTier extends ChatGoogle {
  private serviceTier?: 'standard' | 'priority' | 'flex';

  constructor(fields: ConstructorParameters<typeof ChatGoogle>[0] & { serviceTier?: 'standard' | 'priority' | 'flex' }) {
    const { serviceTier, ...rest } = fields;
    super(rest);
    this.serviceTier = serviceTier;
  }

  invocationParams(options: Parameters<ChatGoogle['invocationParams']>[0]): ReturnType<ChatGoogle['invocationParams']> {
    const params = super.invocationParams(options);
    if (this.serviceTier && this.serviceTier !== 'standard') {
      return { ...params, serviceTier: this.serviceTier } as ReturnType<ChatGoogle['invocationParams']>;
    }
    return params;
  }
}