From b16a28cd6f12d9732bcf6b028fcbe7c62b2d892e Mon Sep 17 00:00:00 2001
From: Ahmad Shahzad <107808273+shzdehmd@users.noreply.github.com>
Date: Fri, 19 Jun 2026 00:18:01 +0500
Subject: [PATCH] feat(vscode): add Fireworks GLM 5.2 and Kimi K2.6 Fast, fix
 DeepSeek V4 Flash cache-read price (#11642)

Update the Fireworks model registry in apps/vscode/src/shared/api.ts:

- Add accounts/fireworks/models/glm-5p2: new general-purpose model with
  a 1,048,576-token context window (131,072 output).
- Add accounts/fireworks/routers/kimi-k2p6-fast: standardizes the
  Kimi K2.6 router on the `-fast` naming convention used for /routers.
  The existing kimi-k2p6-turbo entry is retained for now to avoid
  breaking user workflows; the turbo variant is expected to be removed
  in a future release once the fast variant is the only one served.
- Correct the cache-read price for accounts/fireworks/models/deepseek-v4-flash
  from 0.03 to 0.028 to match the published rate.

Pricing sourced from https://docs.fireworks.ai/serverless/pricing.
---
 apps/vscode/src/shared/api.ts | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/apps/vscode/src/shared/api.ts b/apps/vscode/src/shared/api.ts
index 09e368b68b..9e5cb59fd9 100644
--- a/apps/vscode/src/shared/api.ts
+++ b/apps/vscode/src/shared/api.ts
@@ -5196,6 +5196,18 @@ export const fireworksModels = {
 		description:
 			"Kimi K2.6 Turbo router for high-performance agentic workloads with vision and text reasoning.",
 	},
+	"accounts/fireworks/routers/kimi-k2p6-fast": {
+		maxTokens: 262000,
+		contextWindow: 262000,
+		supportsImages: true,
+		supportsPromptCache: true,
+		inputPrice: 2,
+		outputPrice: 8,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.3,
+		description:
+			"Kimi K2.6 Fast router for high-performance agentic workloads with vision and text reasoning.",
+	},
 	"accounts/fireworks/routers/kimi-k2p7-code-fast": {
 		maxTokens: 262000,
 		contextWindow: 262000,
@@ -5216,7 +5228,7 @@ export const fireworksModels = {
 		inputPrice: 0.14,
 		outputPrice: 0.28,
 		cacheWritesPrice: 0,
-		cacheReadsPrice: 0.03,
+		cacheReadsPrice: 0.028,
 		description:
 			"DeepSeek V4 Flash is a fast, cost-efficient reasoning model with a 1M context window and strong tool-use capabilities.",
 	},
@@ -5232,6 +5244,17 @@ export const fireworksModels = {
 		description:
 			"DeepSeek V4 Pro is a flagship reasoning model with a 1M context window, advanced structured output, and agentic performance.",
 	},
+	"accounts/fireworks/models/glm-5p2": {
+		maxTokens: 131072,
+		contextWindow: 1048576,
+		supportsImages: false,
+		supportsPromptCache: true,
+		inputPrice: 1.4,
+		outputPrice: 4.4,
+		cacheWritesPrice: 0,
+		cacheReadsPrice: 0.26,
+		description: "GLM 5.2 is a next-generation general-purpose model optimized for coding, reasoning, and agentic workflows with a 1M context window.",
+	},
 	"accounts/fireworks/models/glm-5p1": {
 		maxTokens: 131072,
 		contextWindow: 202800,