From 7f5b2bf290f652b12d351c9142eb3db0a1917d99 Mon Sep 17 00:00:00 2001 From: fatih <34196005+fcakyon@users.noreply.github.com> Date: Mon, 1 Jan 2024 11:49:46 +0300 Subject: [PATCH 1/4] fix typos & add missing names for azure models --- model_prices_and_context_window.json | 22 ++++++++++++++++++---- 1 file changed, 18 insertions(+), 4 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index f3005759c7fb..8c239db5547e 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -118,28 +118,42 @@ "litellm_provider": "azure", "mode": "chat" }, + "azure/ggpt-4-32k-0613": { + "max_tokens": 32768, + "input_cost_per_token": 0.00006, + "output_cost_per_token": 0.00012, + "litellm_provider": "azure", + "mode": "chat" + }, "azure/gpt-4-32k": { - "max_tokens": 8192, + "max_tokens": 32768, "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, "litellm_provider": "azure", "mode": "chat" }, "azure/gpt-4": { - "max_tokens": 16385, + "max_tokens": 8192, "input_cost_per_token": 0.00003, "output_cost_per_token": 0.00006, "litellm_provider": "azure", "mode": "chat" }, - "azure/gpt-3.5-turbo-16k": { + "azure/gpt-35-turbo-1106": { + "max_tokens": 16384, + "input_cost_per_token": 0.0000015, + "output_cost_per_token": 0.000002, + "litellm_provider": "azure", + "mode": "chat" + }, + "azure/gpt-35-turbo-16k": { "max_tokens": 16385, "input_cost_per_token": 0.000003, "output_cost_per_token": 0.000004, "litellm_provider": "azure", "mode": "chat" }, - "azure/gpt-3.5-turbo": { + "azure/gpt-35-turbo": { "max_tokens": 4097, "input_cost_per_token": 0.0000015, "output_cost_per_token": 0.000002, From 08d23aafc0db8ad0741517ef7370ad1537a8be8b Mon Sep 17 00:00:00 2001 From: fatih <34196005+fcakyon@users.noreply.github.com> Date: Mon, 1 Jan 2024 11:57:48 +0300 Subject: [PATCH 2/4] fix a typo --- model_prices_and_context_window.json | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 8c239db5547e..81cc754bb0c7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -118,7 +118,7 @@ "litellm_provider": "azure", "mode": "chat" }, - "azure/ggpt-4-32k-0613": { + "azure/gpt-4-32k-0613": { "max_tokens": 32768, "input_cost_per_token": 0.00006, "output_cost_per_token": 0.00012, From 6566ebd815fca21856dfea04b543a68b90161fc9 Mon Sep 17 00:00:00 2001 From: fatih <34196005+fcakyon@users.noreply.github.com> Date: Mon, 1 Jan 2024 13:03:08 +0300 Subject: [PATCH 3/4] update azure turbo namings --- litellm/__init__.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/litellm/__init__.py b/litellm/__init__.py index 1de60c761e35..510832a573ec 100644 --- a/litellm/__init__.py +++ b/litellm/__init__.py @@ -335,9 +335,9 @@ def identify(event_details): # used for token counting # Azure returns gpt-35-turbo in their responses, we need to map this to azure/gpt-3.5-turbo for token counting azure_llms = { - "gpt-35-turbo": "azure/gpt-3.5-turbo", - "gpt-35-turbo-16k": "azure/gpt-3.5-turbo-16k", - "gpt-35-turbo-instruct": "azure/gpt-3.5-turbo-instruct", + "gpt-35-turbo": "azure/gpt-35-turbo", + "gpt-35-turbo-16k": "azure/gpt-35-turbo-16k", + "gpt-35-turbo-instruct": "azure/gpt-35-turbo-instruct", } petals_models = [ From 29ebd23228dd28ab367fbafc85bd62f66f0586b5 Mon Sep 17 00:00:00 2001 From: fatih <34196005+fcakyon@users.noreply.github.com> Date: Mon, 1 Jan 2024 14:13:00 +0300 Subject: [PATCH 4/4] Update model_prices_and_context_window.json --- model_prices_and_context_window.json | 14 ++++++++++++++ 1 file changed, 14 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 81cc754bb0c7..c39b1cda47bb 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -118,6 +118,13 @@ "litellm_provider": "azure", "mode": "chat" }, + "azure/gpt-4-0613": { + "max_tokens": 8192, + "input_cost_per_token": 0.00003, + "output_cost_per_token": 0.00006, + "litellm_provider": "azure", + "mode": "chat" + }, "azure/gpt-4-32k-0613": { "max_tokens": 32768, "input_cost_per_token": 0.00006, @@ -139,6 +146,13 @@ "litellm_provider": "azure", "mode": "chat" }, + "azure/gpt-35-turbo-16k-0613": { + "max_tokens": 16385, + "input_cost_per_token": 0.000003, + "output_cost_per_token": 0.000004, + "litellm_provider": "azure", + "mode": "chat" + }, "azure/gpt-35-turbo-1106": { "max_tokens": 16384, "input_cost_per_token": 0.0000015,