From b267241e33b6b31431dce5ec7b2da4e83da96bad Mon Sep 17 00:00:00 2001
From: Thomas Byr <thomas.bouyer@pm.me>
Date: Fri, 28 Aug 2026 16:40:49 +0200
Subject: [PATCH] feat(pricing): add display pricing for Qwen 3.8 Flash and GLM
 5.3 Flash

Qwen/Qwen3.8-Flash lists $0.16 input, $0.47 output, and $0.016 cache read
per million tokens, and z-ai/glm-5.3-flash lists $0.15, $0.50, and $0.03;
the official pricing page documents no cache-write rate for either model.
---
 src/pricing.ts                            |  2 ++
 tests/fixtures/commandcode-model-ids.json |  2 ++
 tests/fixtures/commandcode-pricing.json   |  2 ++
 tests/test-pricing.ts                     | 12 ++++++++++++
 4 files changed, 18 insertions(+)

diff --git a/src/pricing.ts b/src/pricing.ts
index fddd2a3..71ba138 100644
--- a/src/pricing.ts
+++ b/src/pricing.ts
@@ -54,6 +54,7 @@ export const MODEL_COSTS: Readonly<Record<string, CommandCodeModelCost>> = {
   },
   "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 },
+  "z-ai/glm-5.3-flash": { input: 0.15, output: 0.5, cacheRead: 0.03, cacheWrite: 0 },
   "zai-org/GLM-5.3": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
   "zai-org/GLM-5.2": { input: 1.4, output: 4.4, cacheRead: 0.26, cacheWrite: 0 },
   "zai-org/GLM-5.2-Fast": { input: 3, output: 10.25, cacheRead: 0.5, cacheWrite: 0 },
@@ -84,6 +85,7 @@ export const MODEL_COSTS: Readonly<Record<string, CommandCodeModelCost>> = {
   },
   "Qwen/Qwen3.8-Max": { input: 2, output: 6, cacheRead: 0.25, cacheWrite: 2.5 },
   "Qwen/Qwen3.8-27B": { input: 0.4, output: 3, cacheRead: 0.04, cacheWrite: 0 },
+  "Qwen/Qwen3.8-Flash": { input: 0.16, output: 0.47, cacheRead: 0.016, cacheWrite: 0 },
   "Qwen/Qwen3.7-Max": { input: 2.5, output: 7.5, cacheRead: 0.5, cacheWrite: 3.13 },
   "Qwen/Qwen3.7-Plus": {
     input: 0.4,
diff --git a/tests/fixtures/commandcode-model-ids.json b/tests/fixtures/commandcode-model-ids.json
index 2a69168..15c677c 100644
--- a/tests/fixtures/commandcode-model-ids.json
+++ b/tests/fixtures/commandcode-model-ids.json
@@ -24,6 +24,7 @@
     "moonshotai/Kimi-K2.7-Code-Highspeed",
     "moonshotai/Kimi-K2.6",
     "moonshotai/Kimi-K2.5",
+    "z-ai/glm-5.3-flash",
     "zai-org/GLM-5.3",
     "zai-org/GLM-5.2",
     "zai-org/GLM-5.2-Fast",
@@ -36,6 +37,7 @@
     "xiaomi/mimo-v2.5",
     "Qwen/Qwen3.8-Max",
     "Qwen/Qwen3.8-27B",
+    "Qwen/Qwen3.8-Flash",
     "Qwen/Qwen3.7-Max",
     "Qwen/Qwen3.7-Plus",
     "Qwen/Qwen3.7-Flash",
diff --git a/tests/fixtures/commandcode-pricing.json b/tests/fixtures/commandcode-pricing.json
index c65ae0c..e8a45bb 100644
--- a/tests/fixtures/commandcode-pricing.json
+++ b/tests/fixtures/commandcode-pricing.json
@@ -19,6 +19,7 @@
     "moonshotai/Kimi-K2.7-Code-Highspeed": [1.9, 8, 0.38, 0],
     "moonshotai/Kimi-K2.6": [0.95, 4, 0.16, 0],
     "moonshotai/Kimi-K2.5": [0.6, 3, 0.1, 0],
+    "z-ai/glm-5.3-flash": [0.15, 0.5, 0.03, 0],
     "zai-org/GLM-5.3": [1.4, 4.4, 0.26, 0],
     "zai-org/GLM-5.2": [1.4, 4.4, 0.26, 0],
     "zai-org/GLM-5.2-Fast": [3, 10.25, 0.5, 0],
@@ -31,6 +32,7 @@
     "xiaomi/mimo-v2.5": [0.14, 0.28, 0.0028, 0],
     "Qwen/Qwen3.8-Max": [2, 6, 0.25, 2.5],
     "Qwen/Qwen3.8-27B": [0.4, 3, 0.04, 0],
+    "Qwen/Qwen3.8-Flash": [0.16, 0.47, 0.016, 0],
     "Qwen/Qwen3.7-Max": [2.5, 7.5, 0.5, 3.13],
     "Qwen/Qwen3.7-Plus": [0.4, 1.6, 0.08, 0.5],
     "Qwen/Qwen3.7-Flash": [0.03, 0.13, 0.006, 0.038],
diff --git a/tests/test-pricing.ts b/tests/test-pricing.ts
index d7141a5..1cdc3c8 100644
--- a/tests/test-pricing.ts
+++ b/tests/test-pricing.ts
@@ -144,6 +144,18 @@ describe("MODEL_COSTS pricing overlay", () => {
       cacheRead: 0.04,
       cacheWrite: 0,
     })
+    assertCost("Qwen/Qwen3.8-Flash", {
+      input: 0.16,
+      output: 0.47,
+      cacheRead: 0.016,
+      cacheWrite: 0,
+    })
+    assertCost("z-ai/glm-5.3-flash", {
+      input: 0.15,
+      output: 0.5,
+      cacheRead: 0.03,
+      cacheWrite: 0,
+    })
     assertCost("google/gemini-3.7-flash", {
       input: 0.75,
       output: 3.75,