phoenix/litellm-mirror
0
0
Fork 1
mirror of https://github.com/BerriAI/litellm.git synced 2025-04-26 03:04:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

build(model_prices_and_context_window.json): add new dbrx llama 3.3 model

Browse source 
fixes llama cost calc on databricks
This commit is contained in:
Krrish Dholakia 2024-12-11 13:01:22 -08:00
parent 74917d7b16
commit 5fe77499d2
3 changed files with 29 additions and 1 deletions
Download patch file Download diff file Expand all files Collapse all files

13
litellm/model_prices_and_context_window_backup.json
View file

@ -7265,6 +7265,19 @@
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."}
},
"databricks/meta-llama-3.3-70b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00000100002,
"input_dbu_cost_per_token": 0.000014286,
"output_cost_per_token": 0.00000299999,
"output_dbu_cost_per_token": 0.000042857,
"litellm_provider": "databricks",
"mode": "chat",
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."}
},
"databricks/databricks-dbrx-instruct": {
"max_tokens": 32768,
"max_input_tokens": 32768,

4
litellm/utils.py
View file

@ -4377,6 +4377,9 @@ def _strip_model_name(model: str, custom_llm_provider: Optional[str]) -> str:
):
strip_version = _strip_stable_vertex_version(model_name=model)
return strip_version
elif custom_llm_provider and (custom_llm_provider == "databricks"):
strip_version = _strip_stable_vertex_version(model_name=model)
return strip_version
else:
strip_finetune = _strip_openai_finetune_model_name(model_name=model)
return strip_finetune
@ -4542,7 +4545,6 @@ def get_model_info( # noqa: PLR0915
)
#########################
supported_openai_params = litellm.get_supported_openai_params(
model=model, custom_llm_provider=custom_llm_provider
)

13
model_prices_and_context_window.json
View file

@ -7265,6 +7265,19 @@
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."}
},
"databricks/meta-llama-3.3-70b-instruct": {
"max_tokens": 128000,
"max_input_tokens": 128000,
"max_output_tokens": 128000,
"input_cost_per_token": 0.00000100002,
"input_dbu_cost_per_token": 0.000014286,
"output_cost_per_token": 0.00000299999,
"output_dbu_cost_per_token": 0.000042857,
"litellm_provider": "databricks",
"mode": "chat",
"source": "https://www.databricks.com/product/pricing/foundation-model-serving",
"metadata": {"notes": "Input/output cost per token is dbu cost * $0.070, based on databricks Llama 3.1 70B conversion. Number provided for reference, '*_dbu_cost_per_token' used in actual calculation."}
},
"databricks/databricks-dbrx-instruct": {
"max_tokens": 32768,
"max_input_tokens": 32768,