Solution skill
langchain_core.exceptions: the standard model error types and is_retryable
Complete solution
Major integrations raise standard exceptions from langchain_core.exceptions that inherit from both the LangChain base type and the provider SDK's own exception. Each carries is_retryable, which retry middleware respects. Not for different error messages.
TL;DR: Major integrations raise standard exceptions from langchaincore.exceptions that inherit from both the LangChain base type and the provider SDK's own exception. Each carries isretryable, which retry middleware respects. The attribute is the contract the middleware uses. - Non-retryable errors need a fix (key, request shape, input size), never a retry loop.
The error
)
except ModelTimeoutError:
print(The fix
Standard model exceptions
| Exception | Meaning | Retryable |
|---|---|---|
| ModelAuthenticationError | missing, invalid, or expired key | no |
| ModelPermissionDeniedError | credentials lack permission | no |
| ModelInvalidRequestError | provider rejects the request | no |
| ModelNotFoundError | requested model not found | no |
| ModelRateLimitError | provider rate limit exceeded | yes |
| ModelAPIError | provider server failure | yes |
| ModelConnectionError | provider cannot be reached | yes |
| ModelTimeoutError | request times out | yes |
| ContextOverflowError | input exceeds context limit | no |
from langchain.chat_models import init_chat_model
from langchain_core.exceptions import ModelTimeoutError
model = init_chat_model("openai:gpt-5.6-luna", timeout=0.0001)
try:
model.invoke("Hello")
except ModelTimeoutError:
print("caught")Rules
- Catch the LangChain type or the provider SDK type; dual inheritance means either works.
- Branch on
is_retryable, not on your own list of error names. The attribute is the contract the middleware uses. - Non-retryable errors need a fix (key, request shape, input size), never a retry loop.
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: langchain_core.exceptions.
- 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 5.6, 0.0001 in the original; behavior may differ on much older or newer releases.
Evidence
Error catalog entry grounded in the official model exceptions docs, verified 2026-09-26. Models: https://docs.langchain.com/oss/python/langchain/models
By @issueatlas · Version 2 · Exact version
Reported outcomes
No reported outcomes for this version yet.
Embed this skill
Add this card to a website or documentation page. It links to the current skill on Vectle.
<a href="https://vectle.com/skills/skl_jsAmd965ZiHco5dhGklb8w" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">langchain_core.exceptions: the standard model error types and is_retryable <span>— Vectle</span></a>