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

…odel fixes llama cost calc on databricks
kp-forks · Dec 11, 2024 · 5ec649b · 5ec649b
1 parent 5885ee5
commit 5ec649b
Show file tree

Hide file tree

Showing 3 changed files with 29 additions and 1 deletion.
diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json
@@ -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,

diff --git a/litellm/utils.py b/litellm/utils.py
@@ -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_max_position_embeddings(model_name):
             )
 
         #########################
-
         supported_openai_params = litellm.get_supported_openai_params(
             model=model, custom_llm_provider=custom_llm_provider
         )

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
@@ -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,