Skip to content

feat(google-vertex): update model YAMLs [bot] #1675

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
Open

feat(google-vertex): update model YAMLs [bot] #1675

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
32 changes: 17 additions & 15 deletions providers/google-vertex/anthropic/claude-opus-4-1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,20 +1,21 @@
costs:
- cache_creation_input_token_cost: 0.00001875
cache_creation_input_token_cost_per_hour: 0.00003
cache_read_input_token_cost: 0.0000015
input_cost_per_token: 0.000015
input_cost_per_token_batches: 0.0000075
output_cost_per_token: 0.000075
output_cost_per_token_batches: 0.0000375
- cache_creation_input_token_cost: 1.875e-5
cache_creation_input_token_cost_per_hour: 3e-5
cache_read_input_token_cost: 1.5e-6
input_cost_per_token: 1.5e-5
input_cost_per_token_batches: 7.5e-6
output_cost_per_token: 7.5e-5
output_cost_per_token_batches: 3.75e-5
region: us-east5
- cache_creation_input_token_cost: 0.00001875
cache_creation_input_token_cost_per_hour: 0.00003
cache_read_input_token_cost: 0.0000015
input_cost_per_token: 0.000015
input_cost_per_token_batches: 0.0000075
output_cost_per_token: 0.000075
output_cost_per_token_batches: 0.0000375
- cache_creation_input_token_cost: 1.875e-5
cache_creation_input_token_cost_per_hour: 3e-5
cache_read_input_token_cost: 1.5e-6
input_cost_per_token: 1.5e-5
input_cost_per_token_batches: 7.5e-6
output_cost_per_token: 7.5e-5
output_cost_per_token_batches: 3.75e-5
region: global
deprecationDate: "2026-06-05"
features:
- function_calling
- parallel_function_calling
Expand All @@ -24,6 +25,7 @@ features:
- cache_control
- system_messages
- structured_output
isDeprecated: true
limits:
context_window: 200000
max_input_tokens: 200000
Expand Down Expand Up @@ -51,7 +53,7 @@ sources:
- https://platform.claude.com/docs/en/docs/build-with-claude/claude-on-vertex-ai
- https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/use-claude
- https://platform.claude.com/docs/en/about-claude/model-deprecations
status: active
status: deprecated
supportedModes:
- chat
thinking: true
4 changes: 3 additions & 1 deletion providers/google-vertex/anthropic/claude-opus-4-1@20250805.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -15,13 +15,15 @@ costs:
output_cost_per_token: 7.5e-5
output_cost_per_token_batches: 3.75e-5
region: global
deprecationDate: "2026-06-05"
features:
- function_calling
- tool_choice
- assistant_prefill
- prompt_caching
- cache_control
- system_messages
isDeprecated: true
limits:
context_window: 200000
max_input_tokens: 200000
Expand All @@ -47,7 +49,7 @@ sources:
- https://platform.claude.com/docs/en/about-claude/pricing
- https://platform.claude.com/docs/en/about-claude/model-deprecations
- https://docs.cloud.google.com/vertex-ai/generative-ai/docs/partner-models/claude/opus-4-1
status: active
status: deprecated
supportedModes:
- chat
thinking: true
16 changes: 16 additions & 0 deletions providers/google-vertex/anthropic/claude-opus-4-5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,6 +7,14 @@ costs:
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: us-east5
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: us
- cache_creation_input_token_cost: 0.00000625
cache_creation_input_token_cost_per_hour: 0.00001
cache_read_input_token_cost: 5e-7
Expand All @@ -23,6 +31,14 @@ costs:
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: europe-west1
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: eu
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
Expand Down
12 changes: 12 additions & 0 deletions providers/google-vertex/anthropic/claude-opus-4-5@20251101.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,37 +3,49 @@ costs:
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: us-east5
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: us
- cache_creation_input_token_cost: 0.00000625
cache_creation_input_token_cost_per_hour: 0.00001
cache_read_input_token_cost: 5e-7
input_cost_per_token: 0.000005
input_cost_per_token_batches: 0.0000025
output_cost_per_token: 0.000025
output_cost_per_token_batches: 0.0000125
region: global
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: europe-west1
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: eu
- cache_creation_input_token_cost: 0.000006875
cache_creation_input_token_cost_per_hour: 0.000011
cache_read_input_token_cost: 5.5e-7
input_cost_per_token: 0.0000055
input_cost_per_token_batches: 0.00000275
output_cost_per_token: 0.0000275
output_cost_per_token_batches: 0.00001375
region: asia-southeast1
features:
- function_calling
Expand Down
2 changes: 1 addition & 1 deletion providers/google-vertex/anthropic/claude-sonnet-4-5@20250929.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -134,7 +134,7 @@ limits:
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
tool_use_system_prompt_tokens: 346
tool_use_system_prompt_tokens: 496
modalities:
input:
- text
Expand Down
6 changes: 3 additions & 3 deletions providers/google-vertex/anthropic/claude-sonnet-4-6@default.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -59,8 +59,8 @@ features:
limits:
context_window: 1000000
max_input_tokens: 1000000
max_output_tokens: 64000
max_tokens: 64000
max_output_tokens: 128000
max_tokens: 128000
tool_use_system_prompt_tokens: 497
modalities:
input:
Expand All @@ -73,7 +73,7 @@ mode: chat
model: anthropic/claude-sonnet-4-6@default
params:
- key: max_tokens
maxValue: 64000
maxValue: 128000
- key: temperature
maxValue: 1
provisioning: serverless
Expand Down
3 changes: 2 additions & 1 deletion providers/google-vertex/deepseek-ai/deepseek-ocr-maas.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,3 +1,4 @@
# CUE validation failed — see errors
costs:
- input_cost_per_token: 3e-7
output_cost_per_token: 0.0000012
Expand Down Expand Up @@ -26,4 +27,4 @@ sources:
- https://docs.cloud.google.com/vertex-ai/generative-ai/docs/maas/deepseek
status: active
supportedModes:
- chat
- ocr
3 changes: 2 additions & 1 deletion providers/google-vertex/deepseek-ai/deepseek-v3.1-maas.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
@@ -1,5 +1,6 @@
costs:
- input_cost_per_token: 6e-7
- cache_read_input_token_cost: 6e-8
input_cost_per_token: 6e-7
input_cost_per_token_batches: 3e-7
output_cost_per_token: 0.0000017
output_cost_per_token_batches: 8.5e-7
Expand Down
1 change: 0 additions & 1 deletion providers/google-vertex/deepseek-ai/deepseek-v3.2-maas.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,7 +7,6 @@ costs:
region: global
features:
- function_calling
- structured_output
- system_messages
- tool_choice
- prompt_caching
Expand Down
7 changes: 4 additions & 3 deletions providers/google-vertex/gemini-2.5-flash-image.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -83,12 +83,13 @@ costs:
output_cost_per_token: 0.0000025
output_cost_per_token_batches: 0.00000125
region: europe-central2
deprecationDate: "2026-10-02"
features:
- system_messages
- structured_output
- prompt_caching

@cursor cursor Bot Jul 2, 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.

Conflicting structured output flag

Medium Severity

This PR adds structured_output (and prompt_caching) to gemini-2.5-flash-image.yaml, while the related google/gemini-2.5-flash-image.yaml updated in the same PR still documents that structured output is not supported and omits those features.

Additional Locations (1)
Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 2b1233f. Configure here.

limits:
context_window: 32768
max_input_tokens: 32768
context_window: 65536
max_input_tokens: 65536

@cursor cursor Bot Jul 2, 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.

Dropped deprecation on alias

Medium Severity

This PR removes deprecationDate from gemini-2.5-flash-image.yaml while google/gemini-2.5-flash-image.yaml in the same provider still carries deprecationDate: "2026-10-02" for the same underlying model family.

Additional Locations (1)
Fix in Cursor Fix in Web

Reviewed by Cursor Bugbot for commit 2b1233f. Configure here.

max_output_tokens: 32768
max_tokens: 32768
modalities:
Expand Down
Loading
Loading