From 609075bd1727c7c0dce7aefc4947f0321eb4f712 Mon Sep 17 00:00:00 2001 From: David Manouchehri Date: Wed, 24 Jul 2024 05:29:27 +0000 Subject: [PATCH] Add Llama 3.1 for Bedrock. --- litellm/llms/bedrock_httpx.py | 2 ++ ...model_prices_and_context_window_backup.json | 18 ++++++++++++++++++ model_prices_and_context_window.json | 18 ++++++++++++++++++ 3 files changed, 38 insertions(+) diff --git a/litellm/llms/bedrock_httpx.py b/litellm/llms/bedrock_httpx.py index c3a563ce4..d6c45fb9c 100644 --- a/litellm/llms/bedrock_httpx.py +++ b/litellm/llms/bedrock_httpx.py @@ -76,6 +76,8 @@ BEDROCK_CONVERSE_MODELS = [ "anthropic.claude-v1", "anthropic.claude-instant-v1", "ai21.jamba-instruct-v1:0", + "meta.llama3-1-8b-instruct-v1:0", + "meta.llama3-1-70b-instruct-v1:0", ] diff --git a/litellm/model_prices_and_context_window_backup.json b/litellm/model_prices_and_context_window_backup.json index e9e599945..ef7caf4a7 100644 --- a/litellm/model_prices_and_context_window_backup.json +++ b/litellm/model_prices_and_context_window_backup.json @@ -3643,6 +3643,24 @@ "litellm_provider": "bedrock", "mode": "chat" }, + "meta.llama3-1-8b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "input_cost_per_token": 0.0000004, + "output_cost_per_token": 0.0000006, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "meta.llama3-1-70b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "input_cost_per_token": 0.00000265, + "output_cost_per_token": 0.0000035, + "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 e9e599945..ef7caf4a7 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -3643,6 +3643,24 @@ "litellm_provider": "bedrock", "mode": "chat" }, + "meta.llama3-1-8b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "input_cost_per_token": 0.0000004, + "output_cost_per_token": 0.0000006, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "meta.llama3-1-70b-instruct-v1:0": { + "max_tokens": 128000, + "max_input_tokens": 128000, + "max_output_tokens": 2048, + "input_cost_per_token": 0.00000265, + "output_cost_per_token": 0.0000035, + "litellm_provider": "bedrock", + "mode": "chat" + }, "512-x-512/50-steps/stability.stable-diffusion-xl-v0": { "max_tokens": 77, "max_input_tokens": 77,