Merge remote-tracking branch 'origin/main' into aws-profile-support

src/shared/api.ts

@@ -40,6 +40,8 @@ export interface ApiHandlerOptions {
 	openAiBaseUrl?: string
 	openAiApiKey?: string
 	openAiModelId?: string
+	openAiCustomModelInfo?: ModelInfo
+	openAiUseAzure?: boolean
 	ollamaModelId?: string
 	ollamaBaseUrl?: string
 	lmStudioModelId?: string
@@ -236,6 +238,15 @@ export const bedrockModels = {
 		inputPrice: 0.25,
 		outputPrice: 1.25,
 	},
+	"meta.llama3-3-70b-instruct-v1:0": {
+		maxTokens: 8192,
+		contextWindow: 128_000,
+		supportsImages: false,
+		supportsComputerUse: false,
+		supportsPromptCache: false,
+		inputPrice: 0.72,
+		outputPrice: 0.72,
+	},
 	"meta.llama3-2-90b-instruct-v1:0": {
 		maxTokens: 8192,
 		contextWindow: 128_000,
@@ -413,8 +424,16 @@ export const openAiModelInfoSaneDefaults: ModelInfo = {
 // Gemini
 // https://ai.google.dev/gemini-api/docs/models/gemini
 export type GeminiModelId = keyof typeof geminiModels
-export const geminiDefaultModelId: GeminiModelId = "gemini-2.0-flash-thinking-exp-1219"
+export const geminiDefaultModelId: GeminiModelId = "gemini-2.0-flash-thinking-exp-01-21"
 export const geminiModels = {
+	"gemini-2.0-flash-thinking-exp-01-21": {
+		maxTokens: 65_536,
+		contextWindow: 1_048_576,
+		supportsImages: true,
+		supportsPromptCache: false,
+		inputPrice: 0,
+		outputPrice: 0,
+	},
 	"gemini-2.0-flash-thinking-exp-1219": {
 		maxTokens: 8192,
 		contextWindow: 32_767,