feat(core): mint langchain-model-profiles and add profile property to BaseChatModel (#33728)

libs/model-profiles/README.md

@@ -0,0 +1,66 @@
+# 🦜🪪 langchain-model-profiles
+
+[![PyPI - Version](https://img.shields.io/pypi/v/langchain-model-profiles?label=%20)](https://pypi.org/project/langchain-model-profiles/#history)
+[![PyPI - License](https://img.shields.io/pypi/l/langchain-model-profiles)](https://opensource.org/licenses/MIT)
+[![PyPI - Downloads](https://img.shields.io/pepy/dt/langchain-model-profiles)](https://pypistats.org/packages/langchain-model-profiles)
+[![Twitter](https://img.shields.io/twitter/url/https/twitter.com/langchainai.svg?style=social&label=Follow%20%40LangChainAI)](https://twitter.com/langchainai)
+
+> [!WARNING]
+> This package is currently in development and the API is subject to change.
+
+Centralized reference of LLM capabilities for LangChain chat models.
+
+## Overview
+
+`langchain-model-profiles` enables programmatic access to model capabilities through a `.profile` property on LangChain chat models.
+
+This allows you to query model-specific features such as context window sizes, supported input/output modalities, structured output support, tool calling capabilities, and more.
+
+## Data sources
+
+This package is built on top of the excellent work by the [models.dev](https://github.com/sst/models.dev) project, an open source initiative that provides model capability data.
+
+This package augments the data from models.dev with some additional fields. We intend to keep this aligned with the upstream project as it evolves.
+
+## Installation
+
+```bash
+pip install "langchain[model-profiles]"
+```
+
+Or with uv:
+
+```bash
+uv add "langchain[model-profiles]"
+```
+
+## Usage
+
+Access model capabilities through the `.profile` property on any LangChain chat model:
+
+```python
+# pip install "langchain[openai]"
+
+from langchain.chat_models import init_chat_model
+
+model = init_chat_model("openai:gpt-5")
+profile = model.profile
+
+# Check specific capabilities
+if profile.get("structured_output"):
+    print(f"This model supports a dedicated structured output feature.")
+
+if profile.get("max_input_tokens"):
+    print(f"Max input tokens: {profile.get('max_input_tokens')}")
+
+if profile.get("..."):
+    ...
+```
+
+## Available fields
+
+See `ModelProfile` in [`model_profile.py`](./langchain_model_profiles/model_profile.py) for the full list of available fields and their descriptions.
+
+## License
+
+MIT