Skip to content
Open
Changes from all commits
Commits
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
30 changes: 30 additions & 0 deletions providers/openrouter/openai/gpt-6.1-terra.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,30 @@
costs:
- cache_creation_input_token_cost: 1.25e-6
cache_read_input_token_cost: 5e-8
input_cost_per_token: 1e-6
output_cost_per_token: 5e-6
region: "*"
features:
- function_calling
- json_output
- prompt_caching
- structured_output
- tool_choice
limits:
context_window: 1050000
max_output_tokens: 128000
modalities:
input:
- pdf
- image
- text
output:
- text
mode: chat
model: openai/gpt-6.1-terra
provisioning: serverless
sources:
- https://openrouter.ai/openai/gpt-6.1-terra
supportedModes:
- chat
thinking: true

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 reasoning effort metadata

Medium Severity

The new OpenRouter openai/gpt-6.1-terra entry sets thinking: true but omits a model-level reasoning_effort param. Official OpenAI docs list none, low, medium (default), high, xhigh, and max, and OpenRouter exposes that control. Catalog clients then inherit OpenRouter default.yaml, which includes unsupported minimal and omits max.

Fix in Cursor Fix in Web

Triggered by project rule: Context windows

Reviewed by Cursor Bugbot for commit ebf4bb4. Configure here.

Loading