LangChain with a custom base URL

Python, every model

pip install -U langchain-openai

Python, Claude on ChatAnthropic

pip install -U langchain-anthropic

JavaScript

npm install @langchain/openai @langchain/anthropic @langchain/core

from langchain_anthropic import ChatAnthropic

llm = ChatAnthropic(
    model="claude-opus-5.5",
    base_url="https://aigrow.gg",
    api_key="ag_your_key_here",
    max_tokens=1024,
)

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

const gpt = new ChatOpenAI({
  model: 'gpt-6-astra',
  apiKey: 'ag_your_key_here',
  configuration: { baseURL: 'https://aigrow.gg/v1' },
});

const claude = new ChatAnthropic({
  model: 'claude-opus-5.5',
  apiKey: 'ag_your_key_here',
  anthropicApiUrl: 'https://aigrow.gg',
});

export OPENAI_API_BASE=https://aigrow.gg/v1
export OPENAI_API_KEY=ag_your_key_here
export ANTHROPIC_BASE_URL=https://aigrow.gg
export ANTHROPIC_API_KEY=ag_your_key_here

404 once tools or reasoning are added

ChatOpenAI moved the call to the Responses API, which it does on its own for built-in tools, reasoning settings and some GPT models. use_responses_api=False, as in the block, keeps every call on chat completions.

404 on ChatAnthropic

base_url ends in /v1. ChatAnthropic adds /v1/messages itself, so it is https://aigrow.gg.

The key is sent to OpenAI or Anthropic

The base URL did not reach the model. Pass base_url to ChatOpenAI or ChatAnthropic directly; it wins over every environment variable.

My tool says 401 or authentication error

The key is missing or mistyped. Copy it again from API access on the dashboard, and make sure it is sent as the key, not as a model name. A revoked key fails the same way: create a new one and swap it in.

I get 402 or a message about credit

Your balance is empty. Open API access on the dashboard, redeem a code or buy another pack, and the next request goes through. Nothing else needs to change.

It says 404 or Unknown model

The model has to be one the endpoint serves, for example claude-opus-5.5. The provider’s own spellings work too (claude-opus-5-5, anthropic/claude-opus-5.5), but a dated id or any model outside the catalogue is rejected before the request is forwarded, and nothing is billed. Request GET /v1/models with your key for the live list, or read the ids on the price list.

Requests are rejected with 429

The endpoint’s capacity is shared by every buyer: about 20 requests a minute and 4 at once. Each 429 carries a retry-after header, and the OpenAI and Anthropic SDKs wait that long and retry on their own. In a loop of your own, wait the seconds it names or lower your concurrency.

The model is unavailable right now

A 404 that says the model is not available right now means it is briefly down at the upstream provider, not a problem with your key or balance. Retry in a moment or send the request to another model.

I get a 502 or 503

A transient upstream or configuration hiccup, not a charge against your balance. Retry the request; if it keeps failing, reach us through the store and we will look into it.

LangChain is billed per token at the credit rates in the price list. An agent sends the whole conversation again with each step, so a long task costs more than its last message suggests; the activity log on API access shows what each request cost.

How do I set base_url in LangChain ChatOpenAI?

Pass base_url="https://aigrow.gg/v1" and api_key with your key when you create ChatOpenAI. openai_api_base is another name for the same setting, and OPENAI_API_BASE or OPENAI_BASE_URL in the environment work too.

How do I set a base URL for ChatAnthropic?

Pass base_url="https://aigrow.gg" in Python, or anthropicApiUrl in JavaScript. Leave /v1 off, because the client adds /v1/messages itself. ANTHROPIC_BASE_URL in the environment works too.

Why set use_responses_api=False?

ChatOpenAI switches to the Responses API on its own for built-in tools, reasoning settings and some GPT models, and the endpoint serves chat completions only. False keeps every call there.

Can ChatOpenAI run Claude models?

Yes. The endpoint serves Claude models on the OpenAI protocol too, so model="claude-opus-5.5" works in ChatOpenAI with the same base_url. ChatAnthropic is the way to send them on the Anthropic protocol.

Sources: LangChain ChatOpenAI · LangChain ChatAnthropic reference · LangChain ChatOpenAI for JavaScript. Read 21 October 2026.