cascadeflow

import { ChatOpenAI } from '@langchain/openai';
import { ChatAnthropic } from '@langchain/anthropic';
import { withCascade } from '@cascadeflow/langchain';

const cascade = withCascade({
  drafter: new ChatOpenAI({ model: 'nous/hermes-flash' }),      // $0.15/$0.60 per 1M tokens
  verifier: new ChatAnthropic({ model: 'claude-sonnet-4-5' }),  // $3/$15 per 1M tokens
  qualityThreshold: 0.8, // 80% queries use drafter
});

// Use like any LangChain chat model
const result = await cascade.invoke('Explain quantum computing');

// Optional: Enable LangSmith tracing (see https://smith.langchain.com)
// Set LANGSMITH_API_KEY, LANGSMITH_PROJECT, LANGSMITH_TRACING=true

// Or with LCEL chains
const chain = prompt.pipe(cascade).pipe(new StringOutputParser());

from langchain_openai import ChatOpenAI
from langchain_anthropic import ChatAnthropic
from cascadeflow.integrations.langchain import CascadeFlow

cascade = CascadeFlow(
    drafter=ChatOpenAI(model="nous/hermes-flash"),      # $0.15/$0.60 per 1M tokens
    verifier=ChatAnthropic(model="claude-sonnet-4-5"),  # $3/$15 per 1M tokens
    quality_threshold=0.8,  # 80% queries use drafter
)

---

## License

MIT ©  see [LICENSE](https://github.com/lemony-ai/cascadeflow/blob/main/LICENSE) file.

Free for commercial use. Attribution appreciated but not required.

---