From e16c204003b4c593cacefa61c6aa0da18f00586d Mon Sep 17 00:00:00 2001 From: ishaan-jaff Date: Wed, 28 Feb 2024 17:00:03 -0800 Subject: [PATCH] (feat) track azure models that support function calling --- ...odel_prices_and_context_window_backup.json | 39 +++++++++++++++---- model_prices_and_context_window.json | 39 +++++++++++++++---- 2 files changed, 62 insertions(+), 16 deletions(-) diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index bf82bb2b1f1..352a5410047 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -300,7 +300,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-1106-preview": { "max_tokens": 128000, @@ -309,7 +311,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-0613": { "max_tokens": 8192, @@ -318,7 +322,8 @@ "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-4-32k-0613": { "max_tokens": 32768, @@ -345,7 +350,8 @@ "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-4-turbo": { "max_tokens": 128000, @@ -354,7 +360,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-turbo-vision-preview": { "max_tokens": 128000, @@ -372,7 +380,8 @@ "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-35-turbo-1106": { "max_tokens": 16384, @@ -381,7 +390,20 @@ "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true + }, + "azure/gpt-35-turbo-0125": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-35-turbo-16k": { "max_tokens": 16385, @@ -399,7 +421,8 @@ "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/ada": { "max_tokens": 8191, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index bf82bb2b1f1..352a5410047 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -300,7 +300,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-1106-preview": { "max_tokens": 128000, @@ -309,7 +311,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-0613": { "max_tokens": 8192, @@ -318,7 +322,8 @@ "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-4-32k-0613": { "max_tokens": 32768, @@ -345,7 +350,8 @@ "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-4-turbo": { "max_tokens": 128000, @@ -354,7 +360,9 @@ "input_cost_per_token": 0.00001, "output_cost_per_token": 0.00003, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-4-turbo-vision-preview": { "max_tokens": 128000, @@ -372,7 +380,8 @@ "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/gpt-35-turbo-1106": { "max_tokens": 16384, @@ -381,7 +390,20 @@ "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true + }, + "azure/gpt-35-turbo-0125": { + "max_tokens": 16384, + "max_input_tokens": 16384, + "max_output_tokens": 4096, + "input_cost_per_token": 0.0000005, + "output_cost_per_token": 0.0000015, + "litellm_provider": "azure", + "mode": "chat", + "supports_function_calling": true, + "supports_parallel_function_calling": true }, "azure/gpt-35-turbo-16k": { "max_tokens": 16385, @@ -399,7 +421,8 @@ "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, "litellm_provider": "azure", - "mode": "chat" + "mode": "chat", + "supports_function_calling": true }, "azure/ada": { "max_tokens": 8191,