Fix pricing for Gemini 2.5 Flash (Thinking) (#2773)

* Fix pricing for Gemini 2.5 Flash (Thinking)

* Looks like it's actually $3.50

* We aren't honoring custom thinking token budgets on Vertex yet

Author: cte

src/shared/api.ts

@@ -477,32 +477,13 @@ export const openRouterDefaultModelInfo: ModelInfo = {
 export type VertexModelId = keyof typeof vertexModels
 export const vertexDefaultModelId: VertexModelId = "claude-3-7-sonnet@20250219"
 export const vertexModels = {
-	"gemini-2.0-flash-001": {
-		maxTokens: 8192,
-		contextWindow: 1_048_576,
-		supportsImages: true,
-		supportsPromptCache: false,
-		inputPrice: 0.15,
-		outputPrice: 0.6,
-	},
-	"gemini-2.5-flash-preview-04-17:thinking": {
-		maxTokens: 65_535,
-		contextWindow: 1_048_576,
-		supportsImages: true,
-		supportsPromptCache: false,
-		inputPrice: 0.15,
-		outputPrice: 0.6,
-		thinking: true,
-		maxThinkingTokens: 24_576,
-	},
 	"gemini-2.5-flash-preview-04-17": {
 		maxTokens: 65_535,
 		contextWindow: 1_048_576,
 		supportsImages: true,
 		supportsPromptCache: false,
 		inputPrice: 0.15,
 		outputPrice: 0.6,
-		thinking: false,
 	},
 	"gemini-2.5-pro-preview-03-25": {
 		maxTokens: 65_535,
@@ -528,6 +509,14 @@ export const vertexModels = {
 		inputPrice: 0,
 		outputPrice: 0,
 	},
+	"gemini-2.0-flash-001": {
+		maxTokens: 8192,
+		contextWindow: 1_048_576,
+		supportsImages: true,
+		supportsPromptCache: false,
+		inputPrice: 0.15,
+		outputPrice: 0.6,
+	},
 	"gemini-2.0-flash-lite-001": {
 		maxTokens: 8192,
 		contextWindow: 1_048_576,
@@ -657,7 +646,7 @@ export const geminiModels = {
 		supportsImages: true,
 		supportsPromptCache: false,
 		inputPrice: 0.15,
-		outputPrice: 0.6,
+		outputPrice: 3.5,
 		thinking: true,
 		maxThinkingTokens: 24_576,
 	},