Skip to content

feat(chat): add Qwen3.8 reasoning guidance #284

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

Draft
andrewtlw wants to merge 1 commit into
base: main
Choose a base branch
from
+18 −6
Draft

feat(chat): add Qwen3.8 reasoning guidance #284

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
16 changes: 12 additions & 4 deletions src/groq/resources/chat/completions.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -70,6 +70,7 @@ def create(
"openai/gpt-oss-20b",
"qwen/qwen3-32b",
"qwen/qwen3.6-27b",
"qwen/qwen3.8-27b",
],
],
citation_options: Optional[Literal["enabled", "disabled"]] | Omit = omit,
Expand Down Expand Up @@ -378,8 +379,11 @@ def create(
Positive values penalize new tokens based on whether they appear in the text so
far, increasing the model's likelihood to talk about new topics.

reasoning_effort: qwen3 models support the following values Set to 'none' to disable reasoning.
Set to 'default' or null to let Qwen reason.
reasoning_effort: qwen3 models support `none` to disable reasoning and `default` or null
to use the model default.

qwen/qwen3.8-27b additionally supports `low`, `medium`, and `high`. Its default
is `medium`; `high` selects the model's native `xhigh` mode.

openai/gpt-oss-20b and openai/gpt-oss-120b support 'low', 'medium', or 'high'.
'medium' is the default value.
Expand Down Expand Up @@ -739,6 +743,7 @@ async def create(
"openai/gpt-oss-20b",
"qwen/qwen3-32b",
"qwen/qwen3.6-27b",
"qwen/qwen3.8-27b",
],
],
citation_options: Optional[Literal["enabled", "disabled"]] | Omit = omit,
Expand Down Expand Up @@ -859,8 +864,11 @@ async def create(
Positive values penalize new tokens based on whether they appear in the text so
far, increasing the model's likelihood to talk about new topics.

reasoning_effort: qwen3 models support the following values Set to 'none' to disable reasoning.
Set to 'default' or null to let Qwen reason.
reasoning_effort: qwen3 models support `none` to disable reasoning and `default` or null
to use the model default.

qwen/qwen3.8-27b additionally supports `low`, `medium`, and `high`. Its default
is `medium`; `high` selects the model's native `xhigh` mode.

openai/gpt-oss-20b and openai/gpt-oss-120b support 'low', 'medium', or 'high'.
'medium' is the default value.
Expand Down
8 changes: 6 additions & 2 deletions src/groq/types/chat/completion_create_params.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -54,6 +54,7 @@ class CompletionCreateParams(TypedDict, total=False):
"openai/gpt-oss-20b",
"qwen/qwen3-32b",
"qwen/qwen3.6-27b",
"qwen/qwen3.8-27b",
],
]
]
Expand Down Expand Up @@ -183,8 +184,11 @@ class CompletionCreateParams(TypedDict, total=False):

reasoning_effort: Optional[Literal["none", "default", "low", "medium", "high"]]
"""
qwen3 models support the following values Set to 'none' to disable reasoning.
Set to 'default' or null to let Qwen reason.
qwen3 models support `none` to disable reasoning and `default` or null to use
the model default.

qwen/qwen3.8-27b additionally supports `low`, `medium`, and `high`. Its default
is `medium`; `high` selects the model's native `xhigh` mode.

openai/gpt-oss-20b and openai/gpt-oss-120b support 'low', 'medium', or 'high'.
'medium' is the default value.
Expand Down
Loading