From f47bc7dfa04a704cacce181ff0ce89a672d59358 Mon Sep 17 00:00:00 2001 From: Krrish Dholakia Date: Fri, 29 Dec 2023 13:07:37 +0530 Subject: [PATCH] build(model_prices_and_context_window.json): add bedrock/cohere light, embeddings, and dedicated capacity pricing --- model_prices_and_context_window.json | 49 ++++++++++++++++++++++++++++ 1 file changed, 49 insertions(+) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 707fa40fa..44085a2ed 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -1108,6 +1108,55 @@ "litellm_provider": "bedrock", "mode": "chat" }, + "bedrock/*/1-month-commitment/cohere.command-text-v14": { + "max_tokens": 4096, + "input_cost_per_second": 0.011, + "output_cost_per_second": 0.011, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "bedrock/*/6-month-commitment/cohere.command-text-v14": { + "max_tokens": 4096, + "input_cost_per_second": 0.0066027, + "output_cost_per_second": 0.0066027, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "cohere.command-light-text-v14": { + "max_tokens": 4000, + "input_cost_per_token": 0.0000003, + "output_cost_per_token": 0.0000006, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "bedrock/*/1-month-commitment/cohere.command-light-text-v14": { + "max_tokens": 4096, + "input_cost_per_second": 0.001902, + "output_cost_per_second": 0.001902, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "bedrock/*/6-month-commitment/cohere.command-light-text-v14": { + "max_tokens": 4096, + "input_cost_per_second": 0.0011416, + "output_cost_per_second": 0.0011416, + "litellm_provider": "bedrock", + "mode": "chat" + }, + "cohere.embed-english-v3": { + "max_tokens": 512, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.000000, + "litellm_provider": "bedrock", + "mode": "embedding" + }, + "cohere.embed-multilingual-v3": { + "max_tokens": 512, + "input_cost_per_token": 0.0000001, + "output_cost_per_token": 0.000000, + "litellm_provider": "bedrock", + "mode": "embedding" + }, "meta.llama2-13b-chat-v1": { "max_tokens": 4096, "input_cost_per_token": 0.00000075,