Add Vercel AI Gateway provider support (#1183)

open-sse/config/providers.js

@@ -124,6 +124,10 @@ export const PROVIDERS = {
     baseUrl: "https://api.openai.com/v1/chat/completions",
     format: "openai"
   },
+  "vercel-ai-gateway": {
+    baseUrl: "https://ai-gateway.vercel.sh/v1/chat/completions",
+    format: "openai"
+  },
   glm: {
     baseUrl: "https://api.z.ai/api/anthropic/v1/messages",
     format: "claude",

open-sse/services/model.js

@@ -18,6 +18,8 @@ const ALIAS_TO_PROVIDER_ID = {
   el: "elevenlabs",
   // API Key providers
   openai: "openai",
+  vercel: "vercel-ai-gateway",
+  "vercel-ai-gateway": "vercel-ai-gateway",
   anthropic: "anthropic",
   gemini: "gemini",
   openrouter: "openrouter",

src/app/api/providers/[id]/models/route.js

@@ -239,6 +239,7 @@ const PROVIDER_MODELS_CONFIG = {
   chutes: createOpenAIModelsConfig("https://llm.chutes.ai/v1/models"),
   nvidia: createOpenAIModelsConfig("https://integrate.api.nvidia.com/v1/models"),
   assemblyai: createOpenAIModelsConfig("https://api.assemblyai.com/v1/models"),
+  "vercel-ai-gateway": createOpenAIModelsConfig("https://ai-gateway.vercel.sh/v1/models"),
 
   // Custom resolvers (non-OpenAI-shaped APIs / token-refresh flows)
   kiro: {

src/app/api/providers/[id]/test/testUtils.js

@@ -399,6 +399,10 @@ async function testApiKeyConnection(connection, effectiveProxy = null) {
         const res = await fetchWithConnectionProxy("https://api.openai.com/v1/models", { headers: { Authorization: `Bearer ${connection.apiKey}` } }, effectiveProxy);
         return { valid: res.ok, error: res.ok ? null : "Invalid API key" };
       }
+      case "vercel-ai-gateway": {
+        const res = await fetchWithConnectionProxy("https://ai-gateway.vercel.sh/v1/models", { headers: { Authorization: `Bearer ${connection.apiKey}` } }, effectiveProxy);
+        return { valid: res.ok, error: res.ok ? null : "Invalid API key" };
+      }
       case "anthropic": {
         const res = await fetchWithConnectionProxy("https://api.anthropic.com/v1/messages", {
           method: "POST",

src/app/api/providers/validate/route.js

@@ -251,6 +251,13 @@ export async function POST(request) {
           isValid = openaiRes.ok;
           break;
 
+        case "vercel-ai-gateway":
+          const vercelAiGatewayRes = await fetch("https://ai-gateway.vercel.sh/v1/models", {
+            headers: { "Authorization": `Bearer ${apiKey}` },
+          });
+          isValid = vercelAiGatewayRes.ok;
+          break;
+
         case "anthropic":
           const anthropicRes = await fetch("https://api.anthropic.com/v1/messages", {
             method: "POST",

src/shared/constants/config.js

@@ -75,6 +75,7 @@ export const PROVIDER_ENDPOINTS = {
   "volcengine-ark": "https://ark.cn-beijing.volces.com/api/coding/v3/chat/completions",
   byteplus: "https://ark.ap-southeast.bytepluses.com/api/coding/v3/chat/completions",
   openai: "https://api.openai.com/v1/chat/completions",
+  "vercel-ai-gateway": "https://ai-gateway.vercel.sh/v1/chat/completions",
   anthropic: "https://api.anthropic.com/v1/messages",
   gemini: "https://generativelanguage.googleapis.com/v1beta/models",
   ollama: "https://ollama.com/api/chat",