Initial addition of Lemonade provider.

litellm/__init__.py

@@ -250,6 +250,7 @@ wandb_key: Optional[str] = None
 heroku_key: Optional[str] = None
 cometapi_key: Optional[str] = None
 ovhcloud_key: Optional[str] = None
+lemonade_key: Optional[str] = None
 common_cloud_provider_auth_params: dict = {
     "params": ["project", "region_name", "token"],
     "providers": ["vertex_ai", "bedrock", "watsonx", "azure", "vertex_ai_beta"],
@@ -536,6 +537,7 @@ volcengine_models: Set = set()
 wandb_models: Set = set(WANDB_MODELS)
 ovhcloud_models: Set = set()
 ovhcloud_embedding_models: Set = set()
+lemonade_models: Set = set()
 
 
 def is_bedrock_pricing_only_model(key: str) -> bool:
@@ -756,6 +758,8 @@ def add_known_models():
             ovhcloud_models.add(key)
         elif value.get("litellm_provider") == "ovhcloud-embedding-models":
             ovhcloud_embedding_models.add(key)
+        elif value.get("litellm_provider") == "lemonade":
+            lemonade_models.add(key)
 
 
 add_known_models()
@@ -852,6 +856,7 @@ model_list = list(
     | volcengine_models
     | wandb_models
     | ovhcloud_models
+    | lemonade_models
 )
 
 model_list_set = set(model_list)
@@ -935,6 +940,7 @@ models_by_provider: dict = {
     "volcengine": volcengine_models,
     "wandb": wandb_models,
     "ovhcloud": ovhcloud_models | ovhcloud_embedding_models,
+    "lemonade": lemonade_models,
 }
 
 # mapping for those models which have larger equivalents
@@ -1284,6 +1290,7 @@ from .llms.hyperbolic.chat.transformation import HyperbolicChatConfig
 from .llms.vercel_ai_gateway.chat.transformation import VercelAIGatewayConfig
 from .llms.ovhcloud.chat.transformation import OVHCloudChatConfig
 from .llms.ovhcloud.embedding.transformation import OVHCloudEmbeddingConfig
+from .llms.lemonade.chat.transformation import LemonadeChatConfig
 from .main import *  # type: ignore
 from .integrations import *
 from .llms.custom_httpx.async_client_cleanup import close_litellm_async_clients

litellm/constants.py

@@ -315,6 +315,7 @@ LITELLM_CHAT_PROVIDERS = [
     "vercel_ai_gateway",
     "wandb",
     "ovhcloud",
+    "lemonade"
 ]
 
 LITELLM_EMBEDDING_PROVIDERS_SUPPORTING_INPUT_ARRAY_OF_TOKENS = [

litellm/litellm_core_utils/get_llm_provider_logic.py

@@ -368,6 +368,8 @@ def get_llm_provider(  # noqa: PLR0915
         # bytez models
         elif model.startswith("bytez/"):
             custom_llm_provider = "bytez"
+        elif model.startswith("lemonade/"):
+            custom_llm_provider = "lemonade"
         elif model.startswith("heroku/"):
             custom_llm_provider = "heroku"
         # cometapi models
@@ -379,6 +381,8 @@ def get_llm_provider(  # noqa: PLR0915
             custom_llm_provider = "compactifai"
         elif model.startswith("ovhcloud/"):
             custom_llm_provider = "ovhcloud"
+        elif model.startswith("lemonade/"):
+            custom_llm_provider = "lemonade"
         if not custom_llm_provider:
             if litellm.suppress_debug_info is False:
                 print()  # noqa
@@ -783,6 +787,13 @@ def _get_openai_compatible_provider_info(  # noqa: PLR0915
             or "https://api.inference.wandb.ai/v1"
         )  # type: ignore
         dynamic_api_key = api_key or get_secret_str("WANDB_API_KEY")
+    elif custom_llm_provider == "lemonade":
+        (
+            api_base,
+            dynamic_api_key,
+        ) = litellm.LemonadeChatConfig()._get_openai_compatible_provider_info(
+            api_base, api_key
+        )
 
     if api_base is not None and not isinstance(api_base, str):
         raise Exception("api base needs to be a string. api_base={}".format(api_base))

litellm/main.py

@@ -149,6 +149,7 @@ from .llms.bedrock.chat import BedrockConverseLLM, BedrockLLM
 from .llms.bedrock.embed.embedding import BedrockEmbedding
 from .llms.bedrock.image.image_handler import BedrockImageGeneration
 from .llms.bytez.chat.transformation import BytezChatConfig
+from .llms.lemonade.chat.transformation import LemonadeChatConfig
 from .llms.codestral.completion.handler import CodestralTextCompletion
 from .llms.cohere.embed import handler as cohere_embed
 from .llms.custom_httpx.aiohttp_handler import BaseLLMAIOHTTPHandler
@@ -267,6 +268,7 @@ bytez_transformation = BytezChatConfig()
 heroku_transformation = HerokuChatConfig()
 oci_transformation = OCIChatConfig()
 ovhcloud_transformation = OVHCloudChatConfig()
+lemonade_transformation = LemonadeChatConfig()
 ####### COMPLETION ENDPOINTS ################
 
 
@@ -3545,6 +3547,35 @@ def completion(  # type: ignore # noqa: PLR0915
             )
 
             pass
+        elif custom_llm_provider == "lemonade":
+            api_key = (
+                api_key
+                or litellm.bytez_key
+                or get_secret_str("LEMONADE_API_KEY")
+                or litellm.api_key
+            )
+
+            response = base_llm_http_handler.completion(
+                model=model,
+                messages=messages,
+                headers=headers,
+                model_response=model_response,
+                api_key=api_key,
+                api_base=api_base,
+                acompletion=acompletion,
+                logging_obj=logging,
+                optional_params=optional_params,
+                litellm_params=litellm_params,
+                timeout=timeout,  # type: ignore
+                client=client,
+                custom_llm_provider=custom_llm_provider,
+                encoding=encoding,
+                stream=stream,
+                provider_config=lemonade_transformation,
+            )
+
+            pass
+
 
         elif custom_llm_provider == "ovhcloud" or model in litellm.ovhcloud_models:
             api_key = (

litellm/model_prices_and_context_window_backup.json

@@ -13256,6 +13256,16 @@
         ],
         "supports_tool_choice": false
     },
+    "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "groq/deepseek-r1-distill-llama-70b": {
         "input_cost_per_token": 7.5e-07,
         "litellm_provider": "groq",

litellm/types/utils.py

@@ -2428,6 +2428,7 @@ class LlmProviders(str, Enum):
     DOTPROMPT = "dotprompt"
     WANDB = "wandb"
     OVHCLOUD = "ovhcloud"
+    LEMONADE = "lemonade"
 
 
 # Create a set of all provider values for quick lookup

model_prices_and_context_window.json

@@ -13256,6 +13256,16 @@
         ],
         "supports_tool_choice": false
     },
+    "lemonade/Qwen3-Coder-30B-A3B-Instruct-GGUF": {
+        "input_cost_per_token": 0,
+        "litellm_provider": "lemonade",
+        "max_tokens": 32768,
+        "mode": "chat",
+        "output_cost_per_token": 0,
+        "supports_function_calling": true,
+        "supports_response_schema": true,
+        "supports_tool_choice": true
+    },
     "groq/deepseek-r1-distill-llama-70b": {
         "input_cost_per_token": 7.5e-07,
         "litellm_provider": "groq",