diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index e9e599945..90a6b1283 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -760,6 +760,36 @@ "litellm_provider": "azure_ai", "mode": "chat" }, + "azure_ai/Meta-Llama-31-8B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.00000061, + "litellm_provider": "azure_ai", + "mode": "chat", + "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-8b-instruct-offer?tab=PlansAndPrice" + }, + "azure_ai/Meta-Llama-31-70B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000268, + "output_cost_per_token": 0.00000354, + "litellm_provider": "azure_ai", + "mode": "chat", + "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-70b-instruct-offer?tab=PlansAndPrice" + }, + "azure_ai/Meta-Llama-31-405B-Instruct": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 128000, + "input_cost_per_token": 0.00000533, + "output_cost_per_token": 0.000016, + "litellm_provider": "azure_ai", + "mode": "chat", + "source":"https://azuremarketplace.microsoft.com/en-us/marketplace/apps/metagenai.meta-llama-3-1-405b-instruct-offer?tab=PlansAndPrice" + }, "babbage-002": { "max_tokens": 16384, "max_input_tokens": 16384,