Skip to content

feat(google-gemini): update model YAMLs [bot] #369

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
hganwani-droid wants to merge 1 commit into
base: main
Choose a base branch
from
Open

feat(google-gemini): update model YAMLs [bot] #369

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
6 changes: 6 additions & 0 deletions providers/google-gemini/aqa.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,11 @@
limits:
max_input_tokens: 7168
max_output_tokens: 1024
max_tokens: 1024
modalities:
input:
- text
output:
- text
mode: unknown
model: aqa
10 changes: 8 additions & 2 deletions providers/google-gemini/deep-research-pro-preview-12-2025.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,15 +15,21 @@ costs:
- cost_per_token: 0.000018
from: 200000
features:
- structured_output
- system_messages
limits:
max_input_tokens: 131072
context_window: 1048576
max_input_tokens: 1048576
max_output_tokens: 65536
max_tokens: 65536
modalities:
input:
- text
- image
- audio
- video
- pdf
output:
- text
mode: chat
model: deep-research-pro-preview-12-2025
removeParams:
Expand Down
4 changes: 4 additions & 0 deletions providers/google-gemini/gemini-2.5-flash-native-audio-preview-09-2025.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,15 @@ features:
limits:
max_input_tokens: 131072
max_output_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
- audio
- video
- image
output:
- text
- audio
mode: realtime
model: gemini-2.5-flash-native-audio-preview-09-2025
Expand Down
5 changes: 4 additions & 1 deletion providers/google-gemini/gemini-2.5-flash-native-audio-preview-12-2025.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -12,11 +12,14 @@ features:
limits:
max_input_tokens: 131072
max_output_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
- audio
- image
- video
Copy link

@cursor cursor bot Mar 19, 2026

Choose a reason for hiding this comment

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

Image modality dropped from 12-2025 audio preview

Medium Severity

The image input modality was removed and replaced with video for gemini-2.5-flash-native-audio-preview-12-2025. However, the older gemini-2.5-flash-native-audio-preview-09-2025 model in this same PR correctly retains both image and video. This appears to be an accidental replacement rather than an intentional removal, as both models in this family support image input.

Fix in Cursor Fix in Web

output:
- text
- audio
mode: realtime
model: gemini-2.5-flash-native-audio-preview-12-2025
Expand Down
12 changes: 8 additions & 4 deletions providers/google-gemini/gemini-3.1-flash-image-preview.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,21 +6,25 @@ costs:
output_cost_per_token_batches: 0.0000015
region: "*"
features:
- structured_output
- system_messages
limits:
max_input_tokens: 65536
max_output_tokens: 65536
max_input_tokens: 131072
max_output_tokens: 32768
max_tokens: 32768
modalities:
input:
- text
- image
- pdf
output:
- text
- image
mode: image
model: gemini-3.1-flash-image-preview
params:
- defaultValue: 256
key: max_tokens
maxValue: 65536
maxValue: 32768
minValue: 1
removeParams:
- tool_choice
Expand Down
13 changes: 12 additions & 1 deletion providers/google-gemini/gemini-3.1-flash-lite-preview.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,14 +15,25 @@ features:
- prompt_caching
- structured_output
- tools
- code_execution
limits:
max_input_tokens: 1048576
max_output_tokens: 65536
max_tokens: 65536
messages:
options:
- system
- user
- assistant
modalities:
input:
- audio
- text
- image
- audio
- video
- pdf
output:
- text
mode: chat
model: gemini-3.1-flash-lite-preview
params:
Expand Down
4 changes: 3 additions & 1 deletion providers/google-gemini/gemini-embedding-2-preview.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,17 +4,19 @@ costs:
input_cost_per_image_token: 4.5e-7
input_cost_per_second: 0.00016
input_cost_per_token: 2.e-7
input_cost_per_token_batches: 1.e-7
input_cost_per_video_token: 0.000012
region: "*"
limits:
max_input_tokens: 8192
max_output_tokens: 1
output_vector_size: 3072
modalities:
input:
- text
- audio
- image
- pdf
- video
mode: embedding
model: gemini-embedding-2-preview
removeParams:
Expand Down
9 changes: 8 additions & 1 deletion providers/google-gemini/gemma-3-12b-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,12 +8,19 @@ features:
- system_messages
- tool_choice
limits:
max_input_tokens: 32768
max_input_tokens: 128000
max_output_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
- image
output:
- text
mode: chat
model: gemma-3-12b-it
params:
- key: max_tokens
maxValue: 8192
sources:
- https://huggingface.co/google/gemma-3-12b-it
11 changes: 11 additions & 0 deletions providers/google-gemini/gemma-3-1b-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -11,9 +11,20 @@ features:
- tools
- structured_output
limits:
context_window: 32768
max_input_tokens: 32768
max_output_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
output:
- text
mode: chat
model: gemma-3-1b-it
params:
- key: max_tokens
maxValue: 8192
sources:
- https://ai.google.dev/gemma/docs/core
- https://ai.google.dev/gemma/docs/core/model_card_3
7 changes: 6 additions & 1 deletion providers/google-gemini/gemma-3-4b-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,11 +8,16 @@ features:
- system_messages
- tool_choice
limits:
max_input_tokens: 32768
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 8192
max_tokens: 8192
modalities:
input:
- text
- image
output:
- text
mode: chat
model: gemma-3-4b-it
params:
Expand Down
5 changes: 5 additions & 0 deletions providers/google-gemini/gemma-3n-e2b-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -9,10 +9,15 @@ features:
limits:
max_input_tokens: 8192
max_output_tokens: 2048
max_tokens: 2048
modalities:
input:
- text
- audio
- image
- video
output:
- text
mode: chat
model: gemma-3n-e2b-it
removeParams:
Expand Down
8 changes: 6 additions & 2 deletions providers/google-gemini/gemma-3n-e4b-it.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,15 +5,19 @@ costs:
features:
- system_messages
limits:
max_input_tokens: 8192
max_output_tokens: 2048
context_window: 32000
Copy link

@cursor cursor bot Mar 19, 2026

Choose a reason for hiding this comment

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

Missing token limits after removing max_input/output_tokens

High Severity

The limits section for gemma-3n-e4b-it now only contains context_window: 32000 — both max_input_tokens and max_output_tokens were removed, and max_tokens was never added. Every other model in this provider (including the sibling gemma-3n-e2b-it) retains all three token limit fields alongside context_window. This likely breaks token limit enforcement for this model.

Fix in Cursor Fix in Web

modalities:
input:
- text
- audio
- image
- video
output:
- text
mode: chat
model: gemma-3n-e4b-it
removeParams:
- tool_choice
sources:
- https://ai.google.dev/gemma/docs/3n
- https://ai.google.dev/gemma/docs/gemma-3n/model_card
14 changes: 6 additions & 8 deletions providers/google-gemini/nano-banana-pro-preview.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -8,21 +8,19 @@ costs:
output_cost_per_token: 0.000012
output_cost_per_token_batches: 0.000006
region: "*"
tiered_pricing:
input:
- cost_per_token: 0.000004
from: 200000
output:
- cost_per_token: 0.000018
from: 200000
features:
- structured_output
- system_messages
limits:
max_input_tokens: 131072
max_input_tokens: 65536
max_output_tokens: 32768
max_tokens: 32768
modalities:
input:
- text
- image
output:
- text
- image
mode: image
model: nano-banana-pro-preview
Expand Down
Loading