Checked other resources

• This is a bug, not a usage question.
• I added a clear and descriptive title that summarizes this issue.
• I used the GitHub search to find a similar question and didn't find it.
• I am sure that this is a bug in LangChain rather than my code.
• The bug is not resolved by updating to the latest stable version of LangChain (or the specific integration package).
• This is not related to the langchain-community package.
• I posted a self-contained, minimal, reproducible example. A maintainer can copy it and run it AS IS.

Package (Required)

• langchain
• langchain-openai
• langchain-anthropic
• langchain-classic
• langchain-core
• langchain-cli
• langchain-model-profiles
• langchain-tests
• langchain-text-splitters
• langchain-chroma
• langchain-deepseek
• langchain-exa
• langchain-fireworks
• langchain-groq
• langchain-huggingface
• langchain-mistralai
• langchain-nomic
• langchain-ollama
• langchain-perplexity
• langchain-prompty
• langchain-qdrant
• langchain-xai
• Other / not sure / general

Example Code (Python)

from langchain.agents import create_agent

agent = create_agent(
    model="mistral:ministral-8b-latest",
    system_prompt="Say hello")


for chunk in agent.stream({"messages": "Hello"}):
    print(chunk)

Error Message and Stack Trace (if applicable)

File "/home/eric-burel/code/lbke-ai-tools/.venv/lib/python3.13/site-packages/langchain_mistralai/chat_models.py", line 172, in _raise_on_error
    raise httpx.HTTPStatusError(
    ...<3 lines>...
    )
httpx.HTTPStatusError: Error response 400 while fetching https://api.mistral.ai/v1/chat/completions: {"object":"error","message":"Invalid model: mistral:ministral-8b-latest","type":"invalid_model","param":null,"code":"1500"}

Description

• Provider name "mistral" is recognized as Mistral provider (this can be verified by not installing the proper package, LangChain will detect it and propose to installa langchain_mistralai)
• But it's not properly removed from the model name which ends up being "mistral:mistral-small-latest" for instance instead of just "mistral-small-latest"
• I suspect this will happen with all aliased package, listed in "/home/eric-burel/code/github-various/langchain/libs/langchain_v1/langchain/chat_models/base.py"

I guess aliases should be applied earlier in the process as soon as create_agent is called so the aliased provider name doesn't leak in other parts of langchain.

System Info

openai: 2.8.1
orjson: 3.11.4
packaging: 25.0
pydantic: 2.12.4
pyyaml: 6.0.3
requests: 2.32.5
requests-toolbelt: 1.0.0
tenacity: 9.1.2
tiktoken: 0.12.0
tokenizers: 0.22.1
typing-extensions: 4.15.0
zstandard: 0.25.0