usage_metadata return None in Langgraph Studio

[DmitryKatson]

Checked other resources

• This is a bug, not a usage question. For questions, please use GitHub Discussions.
• I added a clear and detailed title that summarizes the issue.
• I read what a minimal reproducible example is (https://stackoverflow.com/help/minimal-reproducible-example).
• I included a self-contained, minimal example that demonstrates the issue INCLUDING all the relevant imports. The code run AS IS to reproduce the issue.

Example Code

from typing import Dict, Any
from langchain_core.messages import SystemMessage
from langchain_openai import AzureChatOpenAI
from langgraph.graph import START, StateGraph, MessagesState
import os

llm = AzureChatOpenAI(
    azure_deployment=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
    openai_api_version=os.getenv("OPENAI_API_VERSION"),
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    temperature=0
)

# System message
system_message = SystemMessage(content="You are a helpful assistant.")

# Define the basic assistant node
def assistant(state: MessagesState) -> Dict[str, Any]:

    """Basic assistant node that processes messages."""
    result = llm.invoke([system_message] + state["messages"])
    print("Usage metadata: ", result.usage_metadata)
    return {"messages": [result]}

# Build graph
builder = StateGraph(MessagesState)

# Add nodes
builder.add_node("assistant", assistant)

# Set entry and finish points
builder.set_entry_point("assistant")
builder.set_finish_point("assistant")

# Compile graph
graph = builder.compile()

Error Message and Stack Trace (if applicable)

result.usage_metadata is None

Description

When trying to access tokens usage inside the graph - always return None.

result = llm.invoke("hello")
print("Usage metadata: ", result.usage_metadata)

Usage metadata: None.

However if i use just the same code outside of langgraph (in test.py file)

from langchain_openai import AzureChatOpenAI
import os

llm = AzureChatOpenAI(
    azure_deployment=os.getenv("AZURE_OPENAI_DEPLOYMENT_NAME"),
    openai_api_version=os.getenv("OPENAI_API_VERSION"),
    azure_endpoint=os.getenv("AZURE_OPENAI_ENDPOINT"),
    temperature=0
)

result = llm.invoke("hello")
print(result.usage_metadata)

{'input_tokens': 8, 'output_tokens': 11, 'total_tokens': 19, 'input_token_details': {'audio': 0, 'cache_read': 0}, 'output_token_details': {'audio': 0, 'reasoning': 0}}

Same with llm.with_structured_output(myPydanticClass, include_raw=True) - if i use inside the langgraph information about token usage is not returned, but if i run outside - all works as expected.

Am i doing something wrong?

System Info

System Information

OS: Darwin
OS Version: Darwin Kernel Version 24.0.0: Mon Aug 12 20:49:48 PDT 2024; root:xnu-11215.1.10~2/RELEASE_ARM64_T8103
Python Version: 3.12.6 (v3.12.6:a4a2d2b0d85, Sep 6 2024, 16:08:03) [Clang 13.0.0 (clang-1300.0.29.30)]

Package Information

langchain_core: 0.3.46
langchain: 0.3.21
langchain_community: 0.3.20
langsmith: 0.3.18
langchain_openai: 0.3.9
langchain_text_splitters: 0.3.7
langgraph_api: 0.0.31
langgraph_cli: 0.1.77
langgraph_license: Installed. No version info available.
langgraph_sdk: 0.1.58
langgraph_storage: Installed. No version info available.

Optional packages not installed

langserve

Other Dependencies

aiohttp<4.0.0,>=3.8.3: Installed. No version info available.
async-timeout<5.0.0,>=4.0.0;: Installed. No version info available.
click: 8.1.8
cryptography: 43.0.3
dataclasses-json<0.7,>=0.5.7: Installed. No version info available.
httpx: 0.28.1
httpx-sse<1.0.0,>=0.4.0: Installed. No version info available.
jsonpatch<2.0,>=1.33: Installed. No version info available.
jsonschema-rs: 0.29.1
langchain-anthropic;: Installed. No version info available.
langchain-aws;: Installed. No version info available.
langchain-azure-ai;: Installed. No version info available.
langchain-cohere;: Installed. No version info available.
langchain-community;: Installed. No version info available.
langchain-core<1.0.0,>=0.3.45: Installed. No version info available.
langchain-deepseek;: Installed. No version info available.
langchain-fireworks;: Installed. No version info available.
langchain-google-genai;: Installed. No version info available.
langchain-google-vertexai;: Installed. No version info available.
langchain-groq;: Installed. No version info available.
langchain-huggingface;: Installed. No version info available.
langchain-mistralai;: Installed. No version info available.
langchain-ollama;: Installed. No version info available.
langchain-openai;: Installed. No version info available.
langchain-text-splitters<1.0.0,>=0.3.7: Installed. No version info available.
langchain-together;: Installed. No version info available.
langchain-xai;: Installed. No version info available.
langchain<1.0.0,>=0.3.21: Installed. No version info available.
langgraph: 0.3.18
langgraph-checkpoint: 2.0.21
langsmith-pyo3: Installed. No version info available.
langsmith<0.4,>=0.1.125: Installed. No version info available.
langsmith<0.4,>=0.1.17: Installed. No version info available.
numpy<3,>=1.26.2: Installed. No version info available.
openai-agents: Installed. No version info available.
openai<2.0.0,>=1.66.3: Installed. No version info available.
opentelemetry-api: Installed. No version info available.
opentelemetry-exporter-otlp-proto-http: Installed. No version info available.
opentelemetry-sdk: Installed. No version info available.
orjson: 3.10.15
packaging: 24.2
packaging<25,>=23.2: Installed. No version info available.
pydantic: 2.10.6
pydantic-settings<3.0.0,>=2.4.0: Installed. No version info available.
pydantic<3.0.0,>=2.5.2;: Installed. No version info available.
pydantic<3.0.0,>=2.7.4: Installed. No version info available.
pydantic<3.0.0,>=2.7.4;: Installed. No version info available.
pyjwt: 2.10.1
pytest: Installed. No version info available.
python-dotenv: 1.0.1
PyYAML>=5.3: Installed. No version info available.
requests: 2.32.3
requests-toolbelt: 1.0.0
requests<3,>=2: Installed. No version info available.
rich: Installed. No version info available.
SQLAlchemy<3,>=1.4: Installed. No version info available.
sse-starlette: 2.1.3
starlette: 0.46.1
structlog: 25.2.0
tenacity: 9.0.0
tenacity!=8.4.0,<10,>=8.1.0: Installed. No version info available.
tenacity!=8.4.0,<10.0.0,>=8.1.0: Installed. No version info available.
tiktoken<1,>=0.7: Installed. No version info available.
typing-extensions>=4.7: Installed. No version info available.
uvicorn: 0.34.0
watchfiles: 1.0.4
zstandard: 0.23.0

[hinthornw]

Are you sure you're running frmo the same python environment? LangGraph has no concept of llms, etc. so I'm not sure how the two would interact in this way.

[gbaian10]

I'm not sure about the situation with AzureChatOpenAI, but the output from ChatOpenAI seems normal?

from typing import Any

from dotenv import load_dotenv
from langchain_core.messages import SystemMessage
from langchain_openai import ChatOpenAI
from langgraph.graph import MessagesState, StateGraph
from rich import get_console

load_dotenv()
llm = ChatOpenAI(model="gpt-4o-mini")

system_message = SystemMessage(content="You are a helpful assistant.")


def assistant(state: MessagesState) -> dict[str, Any]:
    result = llm.invoke([system_message] + state["messages"])
    print("Usage metadata: ", result.usage_metadata)
    return {"messages": [result]}


builder = StateGraph(MessagesState)
builder.add_node("assistant", assistant)
builder.set_entry_point("assistant")
builder.set_finish_point("assistant")

graph = builder.compile()
result = graph.invoke({"messages": [("human", "hello")]})
get_console().print(result)

[DmitryKatson]

Yes, absolutely.Double checked that the library versions are the same.

[DmitryKatson]

I'm not sure about the situation with AzureChatOpenAI, but the output from ChatOpenAI seems normal?

from typing import Any

from dotenv import load_dotenv
from langchain_core.messages import SystemMessage
from langchain_openai import ChatOpenAI
from langgraph.graph import MessagesState, StateGraph
from rich import get_console

load_dotenv()
llm = ChatOpenAI(model="gpt-4o-mini")

system_message = SystemMessage(content="You are a helpful assistant.")

def assistant(state: MessagesState) -> dict[str, Any]:
result = llm.invoke([system_message] + state["messages"])
print("Usage metadata: ", result.usage_metadata)
return {"messages": [result]}

builder = StateGraph(MessagesState)
builder.add_node("assistant", assistant)
builder.set_entry_point("assistant")
builder.set_finish_point("assistant")

graph = builder.compile()
result = graph.invoke({"messages": [("human", "hello")]})
get_console().print(result)

Interesting.
When I run this code directly i get expected result

But when i use langgraph studio i get None

langgraph dev

[eyurtsev]

When you're running using langgraph dev maybe it's using a different env?

You can use from langchain_core.sys_info import print_sys_info; print_sys_info() to get env information printed out about all packages.

[DmitryKatson]

When you're running using langgraph dev maybe it's using a different env?

You can use from langchain_core.sys_info import print_sys_info; print_sys_info() to get env information printed out about all packages.

Yes, absolutely identical. I reproduced this on the very new fresh vm, installed everything from scratch. langgraph studio and direct python execution, use same environment.

Same issue

[DmitryKatson]

Interesting, that when with this code i start langgraph langgraph dev it runs the graph and i get token usage

and i see this in langsmith traces as well

but when invoke the question through the studio it didn't return the usage_metadata.

If i call this graph through API i get usage_metadata as well

So, for some reason the problem is in calling from studio