From 6fe8c33448e20aa4d5e34ce604c64418126f838c Mon Sep 17 00:00:00 2001 From: Olivier Cornelis <26625900+thiswillbeyourgithub@users.noreply.github.com> Date: Fri, 26 Sep 2025 19:32:30 +0200 Subject: [PATCH] docs: add documentation for additional cost-related keys in custom pricing (#14949) Co-authored-by: aider (openrouter/anthropic/claude-sonnet-4) --- docs/my-website/docs/proxy/custom_pricing.md | 18 ++++++++++++++++++ 1 file changed, 18 insertions(+) diff --git a/docs/my-website/docs/proxy/custom_pricing.md b/docs/my-website/docs/proxy/custom_pricing.md index e2df7721bfb..fc7312b92ac 100644 --- a/docs/my-website/docs/proxy/custom_pricing.md +++ b/docs/my-website/docs/proxy/custom_pricing.md @@ -83,6 +83,24 @@ model_list: cache_read_input_token_cost: 0.0000006 ``` +### Additional Cost Keys + +There are other keys you can use to specify costs for different scenarios and modalities: + +- `input_cost_per_token_above_200k_tokens` - Cost for input tokens when context exceeds 200k tokens +- `output_cost_per_token_above_200k_tokens` - Cost for output tokens when context exceeds 200k tokens +- `cache_creation_input_token_cost_above_200k_tokens` - Cache creation cost for large contexts +- `cache_read_input_token_cost_above_200k_token` - Cache read cost for large contexts +- `input_cost_per_image` - Cost per image in multimodal requests +- `output_cost_per_reasoning_token` - Cost for reasoning tokens (e.g., OpenAI o1 models) +- `input_cost_per_audio_token` - Cost for audio input tokens +- `output_cost_per_audio_token` - Cost for audio output tokens +- `input_cost_per_video_per_second` - Cost per second of video input +- `input_cost_per_video_per_second_above_128k_tokens` - Video cost for large contexts +- `input_cost_per_character` - Character-based pricing for some providers + +These keys evolve based on how new models handle multimodality. The latest version can be found at [https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json](https://github.com/BerriAI/litellm/blob/main/model_prices_and_context_window.json). + ## Set 'base_model' for Cost Tracking (e.g. Azure deployments) **Problem**: Azure returns `gpt-4` in the response when `azure/gpt-4-1106-preview` is used. This leads to inaccurate cost tracking