Skip to content

Add GPT-5.x models with reasoning model warnings #33

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
bharatsb wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Add GPT-5.x models with reasoning model warnings #33

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 5 additions & 1 deletion src/openai_messages_token_helper/model_helper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,13 +40,17 @@
"gpt-5-mini": 272000,
"gpt-5-nano": 272000,
"gpt-5-chat": 128000,
"gpt-5.1": 272000,
"gpt-5.1-chat": 111616,
"gpt-5.2": 272000,
"gpt-5.2-chat": 111616,
}


AOAI_2_OAI = {"gpt-35-turbo": "gpt-3.5-turbo", "gpt-35-turbo-16k": "gpt-3.5-turbo-16k", "gpt-4v": "gpt-4-turbo-vision"}

# Set of reasoning models that cannot have token usage pre-estimated
REASONING_MODELS = {"gpt-5", "gpt-5-mini", "gpt-5-nano"}
REASONING_MODELS = {"gpt-5", "gpt-5-mini", "gpt-5-nano", "gpt-5.1", "gpt-5.1-chat", "gpt-5.2"}

logger = logging.getLogger("openai_messages_token_helper")

Expand Down
4 changes: 4 additions & 0 deletions tests/test_modelhelper.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -20,6 +20,10 @@ def test_get_token_limit():
assert get_token_limit("gpt-5-mini") == 272000
assert get_token_limit("gpt-5-nano") == 272000
assert get_token_limit("gpt-5-chat") == 128000
assert get_token_limit("gpt-5.1") == 272000
assert get_token_limit("gpt-5.1-chat") == 111616
assert get_token_limit("gpt-5.2") == 272000
assert get_token_limit("gpt-5.2-chat") == 111616


def test_get_token_limit_error():
Expand Down