Skip to content

feat(deepinfra/Qwen/Qwen3.8-27B): add new models [bot] #2181

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

Closed
models-bot wants to merge 1 commit into from
Closed

feat(deepinfra/Qwen/Qwen3.8-27B): add new models [bot] #2181

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: 16 additions & 0 deletions providers/deepinfra/Qwen/Qwen3.8-27B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -0,0 +1,16 @@
costs:
- cache_read_input_token_cost: 4e-8
input_cost_per_token: 4e-7
output_cost_per_token: 3e-6
region: "*"
features:
- prompt_caching

@cursor cursor Bot Aug 19, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Missing tool and JSON features

Medium Severity

features only includes prompt_caching. Comparable DeepInfra Qwen chat models (Qwen3.5-27B, Qwen3.8-Max, Qwen3.7-Max) also declare function_calling and json_output, and external docs confirm tool use for Qwen3.8-27B. Capability discovery based on this file will under-report supported features.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit b6302b0. Configure here.

limits:
context_window: 262144
max_tokens: 262144
modalities:
input:
- image

@cursor cursor Bot Aug 19, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Incomplete input and output modalities

High Severity

modalities lists only image input and omits output entirely. Qwen3.8-27B is a vision-language chat model that accepts text (and typically video) and returns text. Sibling configs such as Qwen3.5-27B and Qwen3.8-Max declare text input and text output. Clients relying on this metadata will wrongly assume text is unsupported.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit b6302b0. Configure here.

mode: unknown

@cursor cursor Bot Aug 19, 2026

Copy link
Copy Markdown

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Wrong primary mode set

High Severity

mode is set to unknown for Qwen/Qwen3.8-27B, a chat vision-language model. Sibling DeepInfra Qwen chat models such as Qwen3.5-27B, Qwen3.6-27B, and Qwen3.8-Max use mode: chat. Consumers that route or filter by chat mode will not treat this model as a chat endpoint.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit b6302b0. Configure here.

model: Qwen/Qwen3.8-27B
thinking: true
Loading