From 3293ad745805b65b10d42f26477888d27f462f5c Mon Sep 17 00:00:00 2001 From: David Manouchehri Date: Thu, 25 Jul 2024 19:29:55 +0000 Subject: [PATCH] Add Llama 3.1 405b for Bedrock --- litellm/llms/bedrock_httpx.py | 1 + litellm/model_prices_and_context_window_backup.json | 9 +++++++++ model_prices_and_context_window.json | 9 +++++++++ 3 files changed, 19 insertions(+) diff --git a/litellm/llms/bedrock_httpx.py b/litellm/llms/bedrock_httpx.py index 16c3f60b78..3f06a50b89 100644 --- a/litellm/llms/bedrock_httpx.py +++ b/litellm/llms/bedrock_httpx.py @@ -78,6 +78,7 @@ BEDROCK_CONVERSE_MODELS = [ "ai21.jamba-instruct-v1:0", "meta.llama3-1-8b-instruct-v1:0", "meta.llama3-1-70b-instruct-v1:0", + "meta.llama3-1-405b-instruct-v1:0", ] diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index 667745c306..c05256d348 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3731,6 +3731,15 @@ "litellm_provider": "bedrock", "mode": "chat" }, + "meta.llama3-1-405b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000532, + "output_cost_per_token": 0.000016, + "litellm_provider": "bedrock", + "mode": "chat" + }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "max_tokens": 77, "max_input_tokens": 77, diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 667745c306..c05256d348 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3731,6 +3731,15 @@ "litellm_provider": "bedrock", "mode": "chat" }, + "meta.llama3-1-405b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 4096, + "input_cost_per_token": 0.00000532, + "output_cost_per_token": 0.000016, + "litellm_provider": "bedrock", + "mode": "chat" + }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "max_tokens": 77, "max_input_tokens": 77,