diff --git a/llms/providers/google_genai.py b/llms/providers/google_genai.py index 6b539e5..eadd465 100644 --- a/llms/providers/google_genai.py +++ b/llms/providers/google_genai.py @@ -16,7 +16,8 @@ class GoogleGenAIProvider(BaseProvider): # no support for "textembedding-gecko" "chat-bison-genai": {"prompt": 0.5, "completion": 0.5, "token_limit": 0, "uses_characters": True}, "text-bison-genai": {"prompt": 1.0, "completion": 1.0, "token_limit": 0, "uses_characters": True}, - "gemini-1.5-pro-latest": {"prompt": 1.0, "completion": 1.0, "token_limit": 0, "uses_characters": True}, + "gemini-1.5-pro": {"prompt": 3.5, "completion": 10.5, "token_limit": 128000, "uses_characters": True}, + "gemini-1.5-flash": {"prompt": 0.35, "completion": 1.05, "token_limit": 128000, "uses_characters": True}, } def __init__(self, api_key=None, model=None, **kwargs): diff --git a/llms/providers/groq.py b/llms/providers/groq.py index 6f63c09..38cb659 100644 --- a/llms/providers/groq.py +++ b/llms/providers/groq.py @@ -12,6 +12,7 @@ class GroqProvider(BaseProvider): "llama-3.1-405b-reasoning": {"prompt": 0.59, "completion": 0.79, "token_limit": 131072, "is_chat": True}, "llama-3.1-70b-versatile": {"prompt": 0.59, "completion": 0.79, "token_limit": 131072, "is_chat": True}, "llama-3.1-8b-instant": {"prompt": 0.05, "completion": 0.08, "token_limit": 131072, "is_chat": True}, + "gemma2-9b-it": {"prompt": 0.20, "completion": 0.20, "token_limit": 131072, "is_chat": True}, } def __init__(