Skip to content

feat(databricks): update model YAMLs [bot] #367

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(databricks): update model YAMLs [bot] #367

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
9 changes: 9 additions & 0 deletions providers/databricks/databricks-claude-3-7-sonnet.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,13 +2,22 @@ costs:
- input_cost_per_token: 0.000003
output_cost_per_token: 0.000015
region: "*"
deprecationDate: "2026-04-12"
features:
- function_calling
- tool_choice
- assistant_prefill
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-3-7-sonnet
thinking: true
8 changes: 8 additions & 0 deletions providers/databricks/databricks-claude-haiku-4-5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,9 +6,17 @@ features:
- function_calling
- tool_choice
- assistant_prefill
- system_messages
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-haiku-4-5
8 changes: 8 additions & 0 deletions providers/databricks/databricks-claude-opus-4-1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,16 @@ features:
- tool_choice
- assistant_prefill
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 32000
max_tokens: 32000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-opus-4-1
thinking: true
8 changes: 8 additions & 0 deletions providers/databricks/databricks-claude-opus-4-5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,16 @@ features:
- tool_choice
- assistant_prefill
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-opus-4-5
thinking: true
7 changes: 7 additions & 0 deletions providers/databricks/databricks-claude-opus-4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,5 +10,12 @@ limits:
max_input_tokens: 200000
max_output_tokens: 32000
max_tokens: 32000
modalities:
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 context_window in claude-opus-4 model YAML

Medium Severity

The context_window field was not added to this model's limits, while every other Claude model in this PR (claude-3-7-sonnet, claude-haiku-4-5, claude-opus-4-1, claude-opus-4-5, claude-sonnet-4, claude-sonnet-4-5) received context_window: 200000. Given max_input_tokens is 200000, this omission appears accidental.

Fix in Cursor Fix in Web

input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-opus-4
thinking: true
9 changes: 9 additions & 0 deletions providers/databricks/databricks-claude-sonnet-4-1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -10,5 +10,14 @@ limits:
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
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 context_window in claude-sonnet-4-1 model YAML

Medium Severity

The context_window field was not added to this model's limits, while every other Claude model in this PR received context_window: 200000. The nearly identical databricks-claude-sonnet-4.yaml has context_window: 200000, making this omission inconsistent and likely accidental.

Fix in Cursor Fix in Web

input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-sonnet-4-1
sources:
- https://platform.claude.com/docs/en/docs/about-claude/models
thinking: true
8 changes: 8 additions & 0 deletions providers/databricks/databricks-claude-sonnet-4-5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,16 @@ features:
- tool_choice
- assistant_prefill
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-sonnet-4-5
thinking: true
8 changes: 8 additions & 0 deletions providers/databricks/databricks-claude-sonnet-4.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -7,8 +7,16 @@ features:
- tool_choice
- assistant_prefill
limits:
context_window: 200000
max_input_tokens: 200000
max_output_tokens: 64000
max_tokens: 64000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-claude-sonnet-4
thinking: true
8 changes: 8 additions & 0 deletions providers/databricks/databricks-gemini-2-5-flash.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,16 @@ features:
- function_calling
- tool_choice
limits:
context_window: 1048576
max_input_tokens: 1048576
max_output_tokens: 65535
max_tokens: 65535
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gemini-2-5-flash
thinking: true
11 changes: 11 additions & 0 deletions providers/databricks/databricks-gemini-2-5-pro.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,8 +6,19 @@ features:
- function_calling
- tool_choice
limits:
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: databricks-gemini-2-5-pro
thinking: true
7 changes: 7 additions & 0 deletions providers/databricks/databricks-gemma-3-12b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,15 @@ costs:
output_cost_per_token: 5.e-7
region: "*"
limits:
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 32000
max_tokens: 32000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gemma-3-12b
10 changes: 10 additions & 0 deletions providers/databricks/databricks-gpt-5-1.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,19 @@ costs:
- input_cost_per_token: 0.00000125
output_cost_per_token: 0.00001
region: "*"
features:
- system_messages
limits:
context_window: 400000
max_input_tokens: 272000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gpt-5-1
thinking: true
7 changes: 7 additions & 0 deletions providers/databricks/databricks-gpt-5-mini.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,15 @@ costs:
output_cost_per_token: 0.000002
region: "*"
limits:
context_window: 400000
max_input_tokens: 272000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gpt-5-mini
9 changes: 9 additions & 0 deletions providers/databricks/databricks-gpt-5-nano.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,18 @@ costs:
- input_cost_per_token: 5.e-8
output_cost_per_token: 4.e-7
region: "*"
features:
- system_messages
limits:
context_window: 400000
max_input_tokens: 272000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gpt-5-nano
20 changes: 20 additions & 0 deletions providers/databricks/databricks-gpt-5.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -2,9 +2,29 @@ costs:
- input_cost_per_token: 0.00000125
output_cost_per_token: 0.00001
region: "*"
features:
- function_calling
- system_messages
- tool_choice
- structured_output
- tools
limits:
context_window: 400000
max_input_tokens: 272000
max_output_tokens: 128000
max_tokens: 128000
messages:
options:
- system
- user
- assistant
- developer
modalities:
input:
- text
- image
output:
- text
mode: chat
model: databricks-gpt-5
thinking: true
13 changes: 10 additions & 3 deletions providers/databricks/databricks-gpt-oss-120b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,15 @@ costs:
output_cost_per_token: 6.e-7
region: "*"
limits:
max_input_tokens: 131072
max_output_tokens: 131072
max_tokens: 131072
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
output:
- text
mode: chat
model: databricks-gpt-oss-120b
thinking: true
9 changes: 6 additions & 3 deletions providers/databricks/databricks-gpt-oss-20b.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,11 @@ costs:
output_cost_per_token: 3.e-7
region: "*"
limits:
max_input_tokens: 131072
max_output_tokens: 131072
max_tokens: 131072
context_window: 128000
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.

Token limit fields accidentally removed from gpt-oss-20b model

High Severity

The max_input_tokens, max_output_tokens, and max_tokens fields (previously 131072) were removed entirely instead of being updated. The limits section now only contains context_window: 128000. The sibling model databricks-gpt-oss-120b.yaml correctly retained all three fields (updated to 128000). Any system reading these token limits will get no value, likely causing errors or falling back to incorrect defaults.

Fix in Cursor Fix in Web

modalities:
input:
- text
output:
- text
mode: chat
model: databricks-gpt-oss-20b
3 changes: 3 additions & 0 deletions providers/databricks/databricks-gte-large-en.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -6,5 +6,8 @@ limits:
max_input_tokens: 8192
max_tokens: 8192
output_vector_size: 1024
modalities:
input:
- text
mode: embedding
model: databricks-gte-large-en
1 change: 1 addition & 0 deletions providers/databricks/databricks-llama-2-70b-chat.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ costs:
region: "*"
features:
- tool_choice
isDeprecated: true
limits:
max_input_tokens: 4096
max_output_tokens: 4096
Expand Down
10 changes: 10 additions & 0 deletions providers/databricks/databricks-llama-4-maverick.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,10 +3,20 @@ costs:
output_cost_per_token: 0.0000015
region: "*"
features:
- function_calling
- tool_choice
- structured_output
limits:
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
output:
- text
mode: chat
model: databricks-llama-4-maverick
sources:
- https://docs.databricks.com/aws/en/machine-learning/model-serving/score-foundation-models
1 change: 1 addition & 0 deletions providers/databricks/databricks-meta-llama-3-1-405b-instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ costs:
region: "*"
features:
- tool_choice
isDeprecated: true
limits:
max_input_tokens: 128000
max_output_tokens: 128000
Expand Down
8 changes: 7 additions & 1 deletion providers/databricks/databricks-meta-llama-3-1-8b-instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -3,8 +3,14 @@ costs:
output_cost_per_token: 4.5e-7
region: "*"
limits:
max_input_tokens: 200000
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
output:
- text
mode: chat
model: databricks-meta-llama-3-1-8b-instruct
6 changes: 6 additions & 0 deletions providers/databricks/databricks-meta-llama-3-3-70b-instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -5,8 +5,14 @@ costs:
features:
- tool_choice
limits:
context_window: 128000
max_input_tokens: 128000
max_output_tokens: 128000
max_tokens: 128000
modalities:
input:
- text
output:
- text
mode: chat
model: databricks-meta-llama-3-3-70b-instruct
1 change: 1 addition & 0 deletions providers/databricks/databricks-meta-llama-3-70b-instruct.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -4,6 +4,7 @@ costs:
region: "*"
features:
- tool_choice
isDeprecated: true
limits:
max_input_tokens: 128000
max_output_tokens: 128000
Expand Down
Loading
Loading