From 5a62f60049f1dd16b2253434ccee753a4c394263 Mon Sep 17 00:00:00 2001
From: Patrick Wozniak <email@patwoz.de>
Date: Thu, 28 May 2026 22:05:20 +0200
Subject: [PATCH] fix(models): correct DeepSeek V4 Flash cache rate, add xiaomi
 models

DeepSeek V4 Flash cache-read rate was /bin/bash.01/1M but docs list ~/bin/bash.028.
Added xiaomi/mimo-v2.5-pro and xiaomi/mimo-v2.5 to MODEL_COSTS so they
don't display as zero-cost models (pricing TBD, currently set to 0).
---
 index.ts | 4 +++-
 1 file changed, 3 insertions(+), 1 deletion(-)

diff --git a/index.ts b/index.ts
index e5cb90c..3a92c1f 100644
--- a/index.ts
+++ b/index.ts
@@ -51,7 +51,7 @@ const MODEL_COSTS: Record<string, CommandCodeModelCost> = {
   "google/gemini-3.1-flash-lite": { input: 0.25, output: 1.5, cacheRead: 0.03, cacheWrite: 0 },
   // 4× usage deal: 75% off (permanent, no expiry)
   "deepseek/deepseek-v4-pro": { input: 0.435, output: 0.87, cacheRead: 0.003625, cacheWrite: 0 },
-  "deepseek/deepseek-v4-flash": { input: 0.14, output: 0.28, cacheRead: 0.01, cacheWrite: 0 },
+  "deepseek/deepseek-v4-flash": { input: 0.14, output: 0.28, cacheRead: 0.028, cacheWrite: 0 },
   "moonshotai/Kimi-K2.6": { input: 0.95, output: 4, cacheRead: 0.16, cacheWrite: 0 },
   "moonshotai/Kimi-K2.5": { input: 0.6, output: 3, cacheRead: 0.1, cacheWrite: 0 },
   "zai-org/GLM-5.1": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
@@ -63,6 +63,8 @@ const MODEL_COSTS: Record<string, CommandCodeModelCost> = {
   // 2× usage deal: 50% off through June 22, 2026
   "Qwen/Qwen3.7-Max": { input: 1.25, output: 3.75, cacheRead: 0.25, cacheWrite: 1.56 },
   "stepfun/Step-3.5-Flash": { input: 0.1, output: 0.3, cacheRead: 0.02, cacheWrite: 0 },
+  "xiaomi/mimo-v2.5-pro": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
+  "xiaomi/mimo-v2.5": { input: 0, output: 0, cacheRead: 0, cacheWrite: 0 },
 }
 
 const streamCommandCode = createStreamCommandCode({