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
32 changes: 32 additions & 0 deletions providers/openrouter/minimax/minimax-m3:free.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,32 @@
costs:
- input_cost_per_token: 0.0
output_cost_per_token: 0.0
region: "*"
features:
- function_calling
- json_output
- tool_choice
limits:
context_window: 1048576
max_output_tokens: 943718

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 max output tokens

Medium Severity

max_output_tokens is set to 943718, which exceeds MiniMax M3’s hard output ceiling of 524288 (requests above that return an invalid-params error). The paid sibling minimax-m3.yaml uses 512000. Catalog consumers that trust this limit can request oversized completions and hit API failures.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit ef83c7b. Configure here.

modalities:
input:
- text
- image
- video
output:
- text
mode: chat
model: minimax/minimax-m3:free
params:
- defaultValue: 1
key: temperature
- defaultValue: 0.95
key: top_p
provisioning: serverless
sources:
- https://openrouter.ai/minimax/minimax-m3:free
status: active
supportedModes:
- chat
thinking: true
Loading