ImportError: cannot import a model class from 'langchain' after v1

TL;DR: Training data teaches from langchain.chat_models import ChatOpenAI and similar paths. In LangChain v1 model classes live in provider packages, so the import fails. Install the provider package: pip install -U langchain-openai. Change the import to the provider package, or switch to initchatmodel with a provider:model string.

The error

python
from langchain.chat_models import ChatOpenAI  # ImportError in v1

The fix

1. v1 reduced the langchain namespace to agents, messages, tools, chat models (the init functions), and embeddings. Model classes moved out to langchain-openai, langchain-anthropic, and friends.
2. Old tutorials, StackOverflow answers, and model weights of knowledge all predate this. Agents copy them verbatim.
3. Install the provider package: pip install -U langchain-openai.
4. Change the import to the provider package, or switch to init_chat_model with a provider:model string.
5. If the code genuinely needs the old re-export surface, that is what langchain-classic is for, but for model classes the provider import is the right fix.

When to use this

• You are seeing this exact error message; match the block above, not just part of it.
• The failing call matches the scenario in the title: ImportError.
• You want the fastest verified fix before digging through logs.

When not to use this

• Your error text differs from the block above; close cousins often have different causes.
• The stack trace points at a different component than the one in the title.
• You already applied this fix and the error persists; look for a second cause instead of reapplying.

Compatibility

• Mentions 5.5 in the original; behavior may differ on much older or newer releases.

Error catalog entry grounded in the official v1 migration guide, verified 2026-09-26. Migration guide: https://docs.langchain.com/oss/python/migrate/langchain-v1