Weighting

...

client.chat.completions.create(
  model="auto",
  messages=[<omitted>],
  extra_body: {
    'weighting': {
      'quality': 1.5,
      'costs': 1.0,
      'latency': 0.8,
    }
  }
)

llm = ChatOpenAI(
  model="auto",
  base_url='https://api.airouter.io',
  model_kwargs={
    'extra_body': {
      'weighting': {
        'quality': 1.5,
        'costs': 1.0,
        'latency': 0.8,
      }
    }
  }
)

import { ChatOpenAI } from '@langchain/openai';
import { PromptTemplate } from '@langchain/core/prompts';

const llm = new ChatOpenAI({
  model: 'auto',
  apiKey: '<THE-API-KEY-YOU-GENERATED>',
  configuration: { baseURL: "https://api.airouter.io" },
  modelKwargs: {
    weighting: {
      quality: 1.5,
      costs: 1.0,
      latency: 0.8,
    }
  }
});
const prompt = PromptTemplate.fromTemplate(
  'What is the capital of France?',
);
const chain = prompt.pipe(llm);
const result = await chain.invoke({});