Skip to content

feat(deepinfra): update model YAMLs [bot] #1966

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
models-bot wants to merge 1 commit into
base: main
Choose a base branch
from
+10 −3
Open

feat(deepinfra): update model YAMLs [bot] #1966

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
1 change: 0 additions & 1 deletion providers/deepinfra/Qwen/Qwen3-Max.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -42,4 +42,3 @@ sources:
status: active
supportedModes:
- chat
thinking: true
2 changes: 1 addition & 1 deletion providers/deepinfra/Qwen/Qwen3.6-35B-A3B.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,5 @@
costs:
- input_cost_per_token: 1.5e-7
- input_cost_per_token: 1e-7

@cursor cursor Bot Jul 31, 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.

Incorrect model input pricing

Medium Severity

input_cost_per_token was changed from 1.5e-7 to 1e-7, but DeepInfra’s chat/demo and API pages for Qwen/Qwen3.6-35B-A3B still list $0.15/1M input (1.5e-7). The $0.10 figure appears only on the Voice page, while this YAML is a chat model. Cost estimates will undercount input spend.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 02ef49a. Configure here.

output_cost_per_token: 9.5e-7
region: "*"
features:
Expand Down
2 changes: 1 addition & 1 deletion providers/deepinfra/meta-llama/Meta-Llama-3.1-8B-Instruct-Turbo.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,6 +1,6 @@
costs:
- input_cost_per_token: 2e-8
output_cost_per_token: 3e-8
output_cost_per_token: 4e-8
region: "*"
features:
- function_calling
Expand Down
8 changes: 8 additions & 0 deletions providers/deepinfra/openai/gpt-oss-20b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,14 @@ modalities:
- text
mode: chat
model: openai/gpt-oss-20b
params:
- defaultValue: medium
key: reasoning_effort
supportedValues:
- low
- medium
- high
type: string
provisioning: serverless
sources:
- https://deepinfra.com/openai/gpt-oss-20b
Expand Down
Loading