From 939ea5d936134bf0bbdf7fcb376c1e9ea7bb9fa0 Mon Sep 17 00:00:00 2001 From: ishaan-jaff Date: Sat, 16 Sep 2023 13:03:13 -0700 Subject: [PATCH] docs --- docs/my-website/docs/max_tokens_cost.md | 6 +----- 1 file changed, 1 insertion(+), 5 deletions(-) diff --git a/docs/my-website/docs/max_tokens_cost.md b/docs/my-website/docs/max_tokens_cost.md index 93936c0d60..5447f2e66a 100644 --- a/docs/my-website/docs/max_tokens_cost.md +++ b/docs/my-website/docs/max_tokens_cost.md @@ -1,11 +1,8 @@ # get context window & cost per token -For every LLM LiteLLM allows you to: -* Get model context window -* Get cost per token +100+ LLMs supported: See full list [here](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json) ## using api.litellm.ai -Usage ```shell curl 'https://api.litellm.ai/get_max_tokens?model=claude-2' ``` @@ -21,7 +18,6 @@ curl 'https://api.litellm.ai/get_max_tokens?model=claude-2' ``` ## using the litellm python package -Usage ```python import litellm model_data = litellm.model_cost["gpt-4"]