feat(providers): add SumoPod and X5Lab OpenAI-compatible providers (#5963)

* feat(providers): add SumoPod and X5Lab OpenAI-compatible providers

Both are OpenAI-compatible BYOK aggregator gateways, wired via the
default executor with bearer API-key auth. Neither ships a hardcoded
model list — both use passthroughModels with an empty seed list and a
live /v1/models fetcher, so the catalog always reflects what each
gateway actually serves instead of speculative model IDs.

- SumoPod: https://ai.sumopod.com/v1/chat/completions (sk- keys)
- X5Lab: https://api.x5lab.dev/v1/chat/completions (x5- keys)

Regression guard: tests/unit/sumopod-x5lab-provider.test.ts.

Co-authored-by: Rigel Ramadhani Waloni <rigel8911@gmail.com>
Inspired-by: https://github.com/decolua/9router/pull/1288

* chore(changelog): restore release entries + add sumopod/x5lab bullet

* test(golden): regenerate translate-path for sumopod + x5lab providers

* test(providers): bump APIKEY count 164→166 for sumopod + x5lab

---------

Co-authored-by: Rigel Ramadhani Waloni <rigel8911@gmail.com>

CHANGELOG.md

@@ -25,6 +25,7 @@
 - **feat(providers):** add b.ai as an OpenAI-compatible (API-key) provider. (thanks @DEYLNN)
 - **feat(providers):** add Nube.sh as an OpenAI-compatible (API-key) provider. (thanks @whale9820)
 - **feat(providers):** add Charm Hyper as an OpenAI-compatible (API-key) provider. (thanks @whale9820)
+- **feat(providers):** add SumoPod and X5Lab as OpenAI-compatible (API-key) providers. (thanks @rigelra15)
 
 ### 🔧 Bug Fixes
 

open-sse/config/providers/index.ts

@@ -178,6 +178,8 @@ import { grok_cliProvider } from "./registry/grok-cli/index.ts";
 import { codebuddy_cnProvider } from "./registry/codebuddy-cn/index.ts";
 import { pioneerProvider } from "./registry/pioneer/index.ts";
 import { zenmux_freeProvider } from "./registry/zenmux-free/index.ts";
+import { sumopodProvider } from "./registry/sumopod/index.ts";
+import { x5labProvider } from "./registry/x5lab/index.ts";
 
 export const REGISTRY: Record<string, RegistryEntry> = {
   aimlapi: aimlapiProvider,
@@ -358,4 +360,6 @@ export const REGISTRY: Record<string, RegistryEntry> = {
   "codebuddy-cn": codebuddy_cnProvider,
   pioneer: pioneerProvider,
   "zenmux-free": zenmux_freeProvider,
+  sumopod: sumopodProvider,
+  x5lab: x5labProvider,
 };

open-sse/config/providers/registry/sumopod/index.ts

@@ -0,0 +1,15 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+export const sumopodProvider: RegistryEntry = {
+  id: "sumopod",
+  alias: "sumopod",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://ai.sumopod.com/v1/chat/completions",
+  authType: "apikey",
+  authHeader: "bearer",
+  modelsUrl: "https://ai.sumopod.com/v1/models",
+  defaultContextLength: 128000,
+  models: [],
+  passthroughModels: true,
+};

open-sse/config/providers/registry/x5lab/index.ts

@@ -0,0 +1,15 @@
+import type { RegistryEntry } from "../../shared.ts";
+
+export const x5labProvider: RegistryEntry = {
+  id: "x5lab",
+  alias: "x5lab",
+  format: "openai",
+  executor: "default",
+  baseUrl: "https://api.x5lab.dev/v1/chat/completions",
+  authType: "apikey",
+  authHeader: "bearer",
+  modelsUrl: "https://api.x5lab.dev/v1/models",
+  defaultContextLength: 128000,
+  models: [],
+  passthroughModels: true,
+};

src/shared/constants/config.ts

@@ -20,6 +20,8 @@ export const PROVIDER_ENDPOINTS = {
   openadapter: "https://api.openadapter.in/v1/chat/completions",
   dit: "https://api.dit.ai/v1/chat/completions",
   tokenrouter: "https://api.tokenrouter.com/v1/chat/completions",
+  sumopod: "https://ai.sumopod.com/v1/chat/completions",
+  x5lab: "https://api.x5lab.dev/v1/chat/completions",
   openai: "https://api.openai.com/v1/chat/completions",
   anthropic: "https://api.anthropic.com/v1/messages",
   gemini: "https://generativelanguage.googleapis.com/v1beta/models",

src/shared/constants/providers/apikey/gateways.ts

@@ -602,4 +602,32 @@ export const APIKEY_PROVIDERS_GATEWAYS = {
     apiHint:
       "TokenRouter exposes an OpenAI-compatible chat completions endpoint at https://api.tokenrouter.com/v1/chat/completions, plus a working /v1/models catalog. OmniRoute uses the OpenAI protocol.",
   },
+  sumopod: {
+    id: "sumopod",
+    alias: "sumopod",
+    name: "SumoPod",
+    icon: "router",
+    color: "#2563EB",
+    textIcon: "SP",
+    passthroughModels: true,
+    website: "https://ai.sumopod.com",
+    authHint:
+      "Use your SumoPod API key (sk-...) in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://ai.sumopod.com/v1.",
+    apiHint:
+      "SumoPod exposes an OpenAI-compatible chat completions endpoint at https://ai.sumopod.com/v1/chat/completions, plus a live /v1/models catalog. OmniRoute uses the OpenAI protocol and lists models via passthrough.",
+  },
+  x5lab: {
+    id: "x5lab",
+    alias: "x5lab",
+    name: "X5Lab",
+    icon: "router",
+    color: "#7C3AED",
+    textIcon: "X5",
+    passthroughModels: true,
+    website: "https://x5lab.dev",
+    authHint:
+      "Use your X5Lab API key (x5-...) in Authorization: Bearer <key>. Fully OpenAI-compatible. API base URL: https://api.x5lab.dev/v1.",
+    apiHint:
+      "X5Lab exposes an OpenAI-compatible chat completions endpoint at https://api.x5lab.dev/v1/chat/completions, plus a live /v1/models catalog. OmniRoute uses the OpenAI protocol and lists models via passthrough.",
+  },
 };

tests/snapshots/provider/translate-path.json

@@ -3778,6 +3778,29 @@
       "stream": "https://api.stepfun.com/v1/chat/completions"
     }
   },
+  "sumopod": {
+    "format": "openai",
+    "headers": {
+      "apiKey": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "nonStream": {
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "oauth": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      }
+    },
+    "url": {
+      "nonStream": "https://ai.sumopod.com/v1/chat/completions",
+      "stream": "https://ai.sumopod.com/v1/chat/completions"
+    }
+  },
   "suno": {
     "format": "openai",
     "headers": {
@@ -4264,6 +4287,29 @@
       "stream": "https://server.self-serve.windsurf.com"
     }
   },
+  "x5lab": {
+    "format": "openai",
+    "headers": {
+      "apiKey": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "nonStream": {
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      },
+      "oauth": {
+        "Accept": "text/event-stream",
+        "Authorization": "Bearer <TOK>",
+        "Content-Type": "application/json"
+      }
+    },
+    "url": {
+      "nonStream": "https://api.x5lab.dev/v1/chat/completions",
+      "stream": "https://api.x5lab.dev/v1/chat/completions"
+    }
+  },
   "xai": {
     "format": "openai",
     "headers": {

tests/unit/providers-constants-split.test.ts

@@ -1,7 +1,7 @@
 // Characterization of the providers.ts catalog split (god-file decomposition): the host became a
 // barrel that re-exports 10 data catalogs now living under constants/providers/*, and APIKEY is
 // merged from 6 semantic family files (apikey/<family>.ts). Locks: the public surface (every catalog
-// + helpers still exported), the spread-merge integrity (164 APIKEY entries, no loss/dup), and that
+// + helpers still exported), the spread-merge integrity (166 APIKEY entries, no loss/dup), and that
 // load-time Zod validation still runs. Pure-data move → behavior must be identical.
 import { test } from "node:test";
 import assert from "node:assert/strict";
@@ -31,12 +31,12 @@ test("barrel still exports every catalog + key helpers", () => {
   }
 });
 
-test("APIKEY_PROVIDERS merges the 6 family files into 164 entries (no loss / no dup)", async () => {
+test("APIKEY_PROVIDERS merges the 6 family files into 166 entries (no loss / no dup)", async () => {
   const keys = Object.keys((P as Record<string, object>).APIKEY_PROVIDERS);
-  assert.equal(keys.length, 164);
-  assert.equal(new Set(keys).size, 164, "duplicate keys after spread-merge");
+  assert.equal(keys.length, 166);
+  assert.equal(new Set(keys).size, 166, "duplicate keys after spread-merge");
   // the merged object's entry-count equals the sum of the 6 semantic family files; families are a
-  // strict partition (every provider in exactly one), so the sum must be exactly 164.
+  // strict partition (every provider in exactly one), so the sum must be exactly 166.
   const families: [string, string][] = [
     ["gateways", "APIKEY_PROVIDERS_GATEWAYS"],
     ["frontier-labs", "APIKEY_PROVIDERS_FRONTIER"],
@@ -56,7 +56,7 @@ test("APIKEY_PROVIDERS merges the 6 family files into 164 entries (no loss / no
       seen.add(k);
     }
   }
-  assert.equal(famTotal, 164, "families must partition all 164 providers");
+  assert.equal(famTotal, 166, "families must partition all 166 providers");
 });
 
 test("AI_PROVIDERS Proxy aggregates all sections; lookups resolve", () => {

tests/unit/sumopod-x5lab-provider.test.ts

@@ -0,0 +1,70 @@
+import test from "node:test";
+import assert from "node:assert/strict";
+
+const { APIKEY_PROVIDERS } = await import("../../src/shared/constants/providers.ts");
+const { PROVIDER_ENDPOINTS } = await import("../../src/shared/constants/config.ts");
+const { REGISTRY: providerRegistry } = await import("../../open-sse/config/providerRegistry.ts");
+
+const SUMOPOD_CHAT_URL = "https://ai.sumopod.com/v1/chat/completions";
+const SUMOPOD_MODELS_URL = "https://ai.sumopod.com/v1/models";
+
+const X5LAB_CHAT_URL = "https://api.x5lab.dev/v1/chat/completions";
+const X5LAB_MODELS_URL = "https://api.x5lab.dev/v1/models";
+
+test("SumoPod is registered as an OpenAI-compatible API-key gateway", () => {
+  const entry = APIKEY_PROVIDERS.sumopod;
+  assert.ok(entry, "APIKEY_PROVIDERS.sumopod must be defined");
+  assert.equal(entry.id, "sumopod");
+  assert.equal(entry.alias, "sumopod");
+  assert.equal(entry.name, "SumoPod");
+  assert.equal(entry.website, "https://ai.sumopod.com");
+  assert.equal(entry.passthroughModels, true);
+});
+
+test("X5Lab is registered as an OpenAI-compatible API-key gateway", () => {
+  const entry = APIKEY_PROVIDERS.x5lab;
+  assert.ok(entry, "APIKEY_PROVIDERS.x5lab must be defined");
+  assert.equal(entry.id, "x5lab");
+  assert.equal(entry.alias, "x5lab");
+  assert.equal(entry.name, "X5Lab");
+  assert.equal(entry.website, "https://x5lab.dev");
+  assert.equal(entry.passthroughModels, true);
+});
+
+test("SumoPod exposes the OpenAI-compatible chat completions endpoint", () => {
+  assert.equal(PROVIDER_ENDPOINTS.sumopod, SUMOPOD_CHAT_URL);
+});
+
+test("X5Lab exposes the OpenAI-compatible chat completions endpoint", () => {
+  assert.equal(PROVIDER_ENDPOINTS.x5lab, X5LAB_CHAT_URL);
+});
+
+test("SumoPod registry entry uses OpenAI format with bearer API-key auth and passthrough models", () => {
+  const entry = providerRegistry.sumopod;
+  assert.ok(entry, "providerRegistry.sumopod must be defined");
+  assert.equal(entry.id, "sumopod");
+  assert.equal(entry.alias, "sumopod");
+  assert.equal(entry.format, "openai");
+  assert.equal(entry.executor, "default");
+  assert.equal(entry.authType, "apikey");
+  assert.equal(entry.authHeader, "bearer");
+  assert.equal(entry.baseUrl, SUMOPOD_CHAT_URL);
+  assert.equal(entry.modelsUrl, SUMOPOD_MODELS_URL);
+  assert.equal(entry.passthroughModels, true);
+  assert.deepEqual(entry.models, [], "SumoPod ships no speculative seeded models — passthrough only");
+});
+
+test("X5Lab registry entry uses OpenAI format with bearer API-key auth and passthrough models", () => {
+  const entry = providerRegistry.x5lab;
+  assert.ok(entry, "providerRegistry.x5lab must be defined");
+  assert.equal(entry.id, "x5lab");
+  assert.equal(entry.alias, "x5lab");
+  assert.equal(entry.format, "openai");
+  assert.equal(entry.executor, "default");
+  assert.equal(entry.authType, "apikey");
+  assert.equal(entry.authHeader, "bearer");
+  assert.equal(entry.baseUrl, X5LAB_CHAT_URL);
+  assert.equal(entry.modelsUrl, X5LAB_MODELS_URL);
+  assert.equal(entry.passthroughModels, true);
+  assert.deepEqual(entry.models, [], "X5Lab ships no speculative seeded models — passthrough only");
+});