Merge pull request #758 from Alex-wuhu/novita-integration

feat: add Novita AI as LLM provider

app/api/validate-model/route.ts

@@ -345,11 +345,12 @@ export async function POST(req: Request) {
                 break
             }
 
-            // GLM, Qwen, Kimi, Qiniu - OpenAI compatible
+            // GLM, Qwen, Kimi, Qiniu, Novita - OpenAI compatible
             case "glm":
             case "qwen":
             case "kimi":
-            case "qiniu": {
+            case "qiniu":
+            case "novita": {
                 const baseURL =
                     baseUrl ||
                     PROVIDER_INFO[provider as ProviderName]?.defaultBaseUrl ||

env.example

@@ -1,6 +1,6 @@
 # AI Provider Configuration
 # AI_PROVIDER: Which provider to use
-# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, deepseek, siliconflow, gateway
+# Options: bedrock, openai, anthropic, google, vertexai, azure, ollama, openrouter, deepseek, siliconflow, gateway, novita
 # Default: bedrock
 AI_PROVIDER=bedrock
 
@@ -167,3 +167,8 @@ AI_MODEL=global.anthropic.claude-sonnet-4-5-20250929-v1:0
 # Get your API key from: https://www.qiniu.com/ai/models
 # QINIU_API_KEY=your_qiniu_api_key
 # QINIU_BASE_URL=https://api.qnaigc.com/v1  # Optional, default
+
+# Novita AI Configuration (Optional)
+# Get your API key from: https://novita.ai/dashboard/key
+# NOVITA_API_KEY=your_novita_api_key
+# NOVITA_BASE_URL=https://api.novita.ai/openai  # Optional, default

lib/ai-providers.ts

@@ -28,6 +28,7 @@ export const SINGLE_SYSTEM_PROVIDERS = new Set<ProviderName>([
     "qwen",
     "kimi",
     "qiniu",
+    "novita",
 ])
 
 /**
@@ -98,6 +99,7 @@ const ALLOWED_CLIENT_PROVIDERS: ProviderName[] = [
     "qiniu",
     "kimi",
     "minimax",
+    "novita",
 ]
 
 // Bedrock provider options for Anthropic beta features
@@ -520,7 +522,8 @@ function buildProviderOptions(
         case "glm":
         case "qwen":
         case "kimi":
-        case "qiniu": {
+        case "qiniu":
+        case "novita": {
             // These providers don't have reasoning configs in AI SDK yet
             // Gateway passes through to underlying providers which handle their own configs
             break
@@ -555,6 +558,7 @@ const PROVIDER_ENV_VARS: Record<ProviderName, string | null> = {
     qiniu: "QINIU_API_KEY",
     kimi: "KIMI_API_KEY",
     minimax: "MINIMAX_API_KEY",
+    novita: "NOVITA_API_KEY",
 }
 
 /**
@@ -1258,7 +1262,8 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
         case "glm":
         case "qwen":
         case "qiniu":
-        case "kimi": {
+        case "kimi":
+        case "novita": {
             const envVar = PROVIDER_ENV_VARS[provider]
             if (!envVar) {
                 throw new Error(
@@ -1285,7 +1290,7 @@ export function getAIModel(overrides?: ClientOverrides): ModelConfig {
 
         default:
             throw new Error(
-                `Unknown AI provider: ${provider}. Supported providers: bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax`,
+                `Unknown AI provider: ${provider}. Supported providers: bedrock, openai, anthropic, google, azure, ollama, openrouter, deepseek, siliconflow, sglang, gateway, edgeone, doubao, modelscope, glm, qwen, qiniu, kimi, minimax, novita`,
             )
     }
 

lib/types/model-config.ts

@@ -21,6 +21,7 @@ export type ProviderName =
     | "qiniu"
     | "kimi"
     | "minimax"
+    | "novita"
 
 // Individual model configuration
 export interface ModelConfig {
@@ -101,6 +102,7 @@ export const PROVIDER_LOGO_MAP: Record<string, string> = {
     doubao: "bytedance",
     modelscope: "modelscope",
     minimax: "minimax",
+    novita: "novita",
 }
 
 // Provider metadata
@@ -179,6 +181,10 @@ export const PROVIDER_INFO: Record<
         label: "MiniMax",
         defaultBaseUrl: "https://api.minimaxi.com/anthropic",
     },
+    novita: {
+        label: "Novita AI",
+        defaultBaseUrl: "https://api.novita.ai/openai",
+    },
 }
 
 // Suggested models per provider for quick add
@@ -350,6 +356,12 @@ export const SUGGESTED_MODELS: Partial<Record<ProviderName, string[]>> = {
         "MiniMax-M2.5",
         "MiniMax-M2.5-highspeed",
     ],
+    novita: [
+        // Novita AI models (OpenAI-compatible API)
+        "moonshotai/kimi-k2.5",
+        "zai-org/glm-5",
+        "minimax/minimax-m2.5",
+    ],
 }
 
 // Helper to generate UUID