Getting structured output using OpenRouter.ai through LangChain

[adocherty]

Checked other resources

• I added a very descriptive title to this question.
• I searched the LangChain documentation with the integrated search.
• I used the GitHub search to find a similar question and didn't find it.

Commit to Help

• I commit to help with one of those options 👆

Example Code

from langchain_openai import ChatOpenAI
from pydantic import BaseModel, Field

selected_model = "meta-llama/llama-3.3-70b-instruct"

llm_model = ChatOpenAI(
    model=selected_model,
    openai_api_key=OPENROUTER_API_KEY,
    openai_api_base=OPENROUTER_BASE_URL,
)

class Joke(BaseModel):
    """Joke to tell user."""

    setup: str = Field(description="The setup of the joke")
    punchline: str = Field(description="The punchline to the joke")
    rating: int = Field(description="How funny the joke is, from 1 to 10")
    
structured_llm = llm_model_openai.with_structured_output(
	Joke.model_json_schema(), method="json_schema"
)
structured_llm.invoke("Tell me a joke about cats")

Description

I’m attempting to use LangChain with OpenRouter to get structured outputs. This works fine for OpenAI models but for other models we require the following parameter to be sent with the request:

provider={"require_parameters": True},

Using a manual request works, for example:

import requests
import json

response = requests.post(
    url=f"{OPENROUTER_BASE_URL}/chat/completions",
    headers={
        "Authorization": f"Bearer {OPENROUTER_API_KEY}",
        "Content-Type": "application/json",
    },
    data=json.dumps(
        dict(
            model=selected_model,
            messages=[
                {"role": "user", "content": "..."},
            ],
            provider={"require_parameters": True},
            response_format={"type": "json_schema", "json_schema": json_schema},
        )
    ),
)

Is there a way to get the ChatOpenAI class to insert this parameter into the calls to the API? Any suggestions for how this could be done would be appreciated!

System Info

System Information

OS: Linux
OS Version: #53-Ubuntu SMP PREEMPT_DYNAMIC Sat Jan 11 00:06:25 UTC 2025
Python Version: 3.12.3 (main, Jan 17 2025, 18:03:48) [GCC 13.3.0]

Package Information

langchain_core: 0.3.33
langchain: 0.3.17
langsmith: 0.3.4
langchain_anthropic: 0.2.4
langchain_ollama: 0.2.0
langchain_openai: 0.2.14
langchain_text_splitters: 0.3.5

Optional packages not installed

langserve

Other Dependencies

jsonpatch: 1.33
openai: 1.58.1
orjson: 3.10.11
pydantic: 2.9.2
requests: 2.32.3
requests-toolbelt: 1.0.0
rich: 13.9.4
tenacity: 9.0.0
tiktoken: 0.8.0
typing-extensions: 4.12.2
zstandard: 0.23.0