LangChain with 6bee.ai

Before you start

Create an account with a verified email address, add prepaid balance, then create a key on the console's API keys page. Keep the key secret.

Model IDs are listed in the console and returned by GET https://api.6bee.ai/v1/models. Replace <model id> with one of them.

Python

from langchain_openai import ChatOpenAI   # pip install langchain-openai

llm = ChatOpenAI(model="<model id>", base_url="https://api.6bee.ai/v1",
                 api_key="<your key>", max_tokens=2048)
print(llm.invoke("Explain this stack trace").content)

JavaScript

import { ChatOpenAI } from '@langchain/openai'; // npm install @langchain/openai

const llm = new ChatOpenAI({
  model: '<model id>', apiKey: process.env.SIXBEE_API_KEY, maxTokens: 2048,
  configuration: { baseURL: 'https://api.6bee.ai/v1' },
});
console.log((await llm.invoke('Explain this stack trace')).content);

Agents and batches

An account runs 2 requests at a time. LangChain’s batch calls and multi-agent graphs run many in parallel by default, so cap them:

answers = llm.batch(prompts, config={"max_concurrency": 2})

Input tokens

1,000,000 uncached tokens per rolling minute. Cache hits don’t count.

Requests

60 per minute.

Concurrency

2 requests at a time.

Tool calling works on models that implement it. Behaviour differs between models, so test the one you plan to use.

Troubleshooting

HTTP 401

The key is missing or wrong. Copy it again from the console, without spaces or quotes.

Model not found

The model ID does not match. List the valid IDs with GET /v1/models or check the console.

HTTP 429

You are over a per-account limit (requests, input tokens or concurrency). The Retry-After header says how long to wait.

HTTP 400 on long sessions

The request no longer fits the model’s context window. Compact or clear the conversation, or switch to a model with a larger window.

Request rejected for balance

Each request first reserves its input plus max_tokens of output. Top up, or lower max_tokens.