From 8e40186764f05a2dc5baf117c761ded23e1d8c5a Mon Sep 17 00:00:00 2001 From: Dotify71 Date: Thu, 21 May 2026 00:12:23 +0530 Subject: [PATCH] fix: update deepseek-v4 prices to active discounted rates --- model_prices_and_context_window.json | 20 ++++++++++---------- 1 file changed, 10 insertions(+), 10 deletions(-) diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json index 6ddcdc7a961..cf4b252b326 100644 --- a/model_prices_and_context_window.json +++ b/model_prices_and_context_window.json @@ -9925,7 +9925,7 @@ "supports_tool_choice": false }, "deepseek-v4-flash": { - "cache_read_input_token_cost": 1.4e-08, + "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, "litellm_provider": "deepseek", "max_input_tokens": 1000000, @@ -9946,14 +9946,14 @@ "supports_tool_choice": true }, "deepseek-v4-pro": { - "cache_read_input_token_cost": 1.74e-07, - "input_cost_per_token": 1.74e-06, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.48e-06, + "output_cost_per_token": 8.7e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions" @@ -12575,9 +12575,9 @@ }, "deepseek/deepseek-v4-flash": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1.4e-08, + "cache_read_input_token_cost": 2.8e-09, "input_cost_per_token": 1.4e-07, - "input_cost_per_token_cache_hit": 1.4e-08, + "input_cost_per_token_cache_hit": 2.8e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 8192, @@ -12599,15 +12599,15 @@ }, "deepseek/deepseek-v4-pro": { "cache_creation_input_token_cost": 0.0, - "cache_read_input_token_cost": 1.74e-07, - "input_cost_per_token": 1.74e-06, - "input_cost_per_token_cache_hit": 1.74e-07, + "cache_read_input_token_cost": 3.625e-09, + "input_cost_per_token": 4.35e-07, + "input_cost_per_token_cache_hit": 3.625e-09, "litellm_provider": "deepseek", "max_input_tokens": 1000000, "max_output_tokens": 8192, "max_tokens": 8192, "mode": "chat", - "output_cost_per_token": 3.48e-06, + "output_cost_per_token": 8.7e-07, "source": "https://api-docs.deepseek.com/quick_start/pricing", "supported_endpoints": [ "/v1/chat/completions"