scriptoriumadmin/litellm
1
0
Fork 0
mirror of https://github.com/BerriAI/litellm.git synced 2026-10-29 06:33:28 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 200

fix(databricks): price the openjev decision model at its published 0.6 DBU per 1M input tokens (#48694)

Browse source 
Co-authored-by: devin-ai-integration[bot] <158243242+devin-ai-integration[bot]@users.noreply.github.com>
This commit is contained in:
Kerry Lu 2026-10-27 18:49:16 -07:00 • committed by GitHub
parent b9e3587721
commit 017e08aba3
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
4 changed files with 19 additions and 13 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

10
litellm/model_prices_and_context_window_backup.json
View file

@ -22042,15 +22042,17 @@
"source": "https://www.databricks.com/product/pricing/foundation-model-serving"
},
"databricks/databricks-openjev-qwen35-4b": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 0.0,
"input_cost_per_token": 0.0,
"cache_creation_input_token_cost": 4.2e-08,
"cache_read_input_token_cost": 4.2e-08,
"input_cost_per_token": 4.2e-08,
"input_dbu_cost_per_token": 6e-07,
"litellm_provider": "databricks",
"metadata": {
"notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost."
"notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate."
},
"mode": "evaluation",
"output_cost_per_token": 0.0,
"output_dbu_cost_per_token": 0.0,
"source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
},
"databricks/ai_decide": {

10
model_prices_and_context_window.json
View file

@ -22042,15 +22042,17 @@
"source": "https://www.databricks.com/product/pricing/foundation-model-serving"
},
"databricks/databricks-openjev-qwen35-4b": {
"cache_creation_input_token_cost": 0.0,
"cache_read_input_token_cost": 0.0,
"input_cost_per_token": 0.0,
"cache_creation_input_token_cost": 4.2e-08,
"cache_read_input_token_cost": 4.2e-08,
"input_cost_per_token": 4.2e-08,
"input_dbu_cost_per_token": 6e-07,
"litellm_provider": "databricks",
"metadata": {
"notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. Databricks published no DBU rate for it as of 2026-10-07, so a deployment's model_info prices set the billed cost."
"notes": "Pay-per-token Foundation Model API decision endpoint (OpenJev, Qwen 3.5 4B) queried through the System One API. The serving-endpoints API lists it at 0.6 DBUs per 1M input tokens (input_price on the foundation_model entry, read 2026-10-27); input_cost_per_token is that dbu cost * $0.070, the same conversion as the other databricks rows. Output is free. Databricks publishes no cache rates for it, so cache tokens bill at the input rate."
},
"mode": "evaluation",
"output_cost_per_token": 0.0,
"output_dbu_cost_per_token": 0.0,
"source": "https://docs.databricks.com/aws/en/machine-learning/foundation-model-apis/supported-models"
},
"databricks/ai_decide": {

8
tests/integration/cost_calculation/cases/decisions.py
View file

@ -332,8 +332,8 @@ DATABRICKS_OPENJEV_QWEN35_4B_DECISIONS: Final = CostTrackingTestCase(
},
),
expected=ExactExpected(
spend=0.0,
input_cost=0.0,
spend=1.89e-06,
input_cost=1.89e-06,
output_cost=0.0,
prompt_tokens=45,
completion_tokens=0,
@ -363,8 +363,8 @@ DATABRICKS_OPENJEV_QWEN35_4B_SYSTEMONE: Final = CostTrackingTestCase(
},
),
expected=ExactExpected(
spend=0.0,
input_cost=0.0,
spend=1.89e-06,
input_cost=1.89e-06,
output_cost=0.0,
prompt_tokens=45,
completion_tokens=0,

4
tests/integration/cost_calculation/cost_map.py
View file

@ -137,7 +137,9 @@ COST_MAP_ENTRIES: Final[dict[str, dict[str, JsonValue]]] = {
"databricks/databricks-openjev-qwen35-4b": {
"litellm_provider": "databricks",
"mode": "evaluation",
"input_cost_per_token": 0.0,
"input_cost_per_token": 4.2e-08,
"cache_read_input_token_cost": 4.2e-08,
"cache_creation_input_token_cost": 4.2e-08,
"output_cost_per_token": 0.0,
},
"openrouter/typesafe/jev-1.13": {