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
26 changes: 26 additions & 0 deletions providers/openrouter/aion-labs/aion-3.0-mini.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,26 @@
costs:
- cache_read_input_token_cost: 1.8e-7
input_cost_per_token: 7e-7
output_cost_per_token: 1.4e-6
region: "*"
features:
- function_calling
- json_output
- prompt_caching
- tool_choice
limits:
context_window: 131072
max_output_tokens: 32768

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 limits max_tokens field

Medium Severity

The new entry sets limits.max_output_tokens to 32768 but omits limits.max_tokens, unlike every other OpenRouter model with the same output cap. With openrouter/default.yaml still bounding the max_tokens request param at 4096, consumers that rely on limits.max_tokens can treat this model as capped far below its advertised 32K output.

Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 69bfc93. Configure here.

modalities:
input:
- text
output:
- text
mode: chat
model: aion-labs/aion-3.0-mini
provisioning: serverless
sources:
- https://openrouter.ai/aion-labs/aion-3.0-mini
supportedModes:
- chat
thinking: true
Loading