From 9482e771ad103a57f092b9d27b35cde1bbf84b10 Mon Sep 17 00:00:00 2001
From: Dushyant Acharya <dushyantacharya@Dushyants-MacBook-Pro.local>
Date: Sun, 3 May 2026 00:03:52 +0530
Subject: [PATCH] feat(cost): add cost mapping for deepseek-v4-flash and
 deepseek-v4-pro

Adds pricing entries for the two new DeepSeek V4 models released on
2026-04-24, for both bare model names and the deepseek/ provider prefix.

Prices sourced from https://api-docs.deepseek.com/quick_start/pricing:
- deepseek-v4-flash: $0.14/M input, $0.28/M output
- deepseek-v4-pro:   $1.74/M input, $3.48/M output

Cache hit price set to 1/10 of input (per DeepSeek docs).
Context window: 1M tokens for both models.

Closes #26709
---
 model_prices_and_context_window.json | 48 ++++++++++++++++++++++++++++
 1 file changed, 48 insertions(+)

diff --git a/model_prices_and_context_window.json b/model_prices_and_context_window.json
index a3b8499d8a5..6ddcdc7a961 100644
--- a/model_prices_and_context_window.json
+++ b/model_prices_and_context_window.json
@@ -12573,6 +12573,54 @@
         "supports_system_messages": true,
         "supports_tool_choice": false
     },
+    "deepseek/deepseek-v4-flash": {
+        "cache_creation_input_token_cost": 0.0,
+        "cache_read_input_token_cost": 1.4e-08,
+        "input_cost_per_token": 1.4e-07,
+        "input_cost_per_token_cache_hit": 1.4e-08,
+        "litellm_provider": "deepseek",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 2.8e-07,
+        "source": "https://api-docs.deepseek.com/quick_start/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
+    "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,
+        "litellm_provider": "deepseek",
+        "max_input_tokens": 1000000,
+        "max_output_tokens": 8192,
+        "max_tokens": 8192,
+        "mode": "chat",
+        "output_cost_per_token": 3.48e-06,
+        "source": "https://api-docs.deepseek.com/quick_start/pricing",
+        "supported_endpoints": [
+            "/v1/chat/completions"
+        ],
+        "supports_assistant_prefill": true,
+        "supports_function_calling": true,
+        "supports_native_streaming": true,
+        "supports_parallel_function_calling": true,
+        "supports_prompt_caching": true,
+        "supports_response_schema": true,
+        "supports_system_messages": true,
+        "supports_tool_choice": true
+    },
     "deepseek/deepseek-v3": {
         "cache_creation_input_token_cost": 0.0,
         "cache_read_input_token_cost": 7e-08,