diff --git a/src/core/search/hybrid.ts b/src/core/search/hybrid.ts
index ecbba2b0d..d6d7b1590 100644
--- a/src/core/search/hybrid.ts
+++ b/src/core/search/hybrid.ts
@@ -1132,7 +1132,29 @@ export async function hybridSearch(
   // provider (Voyage, ZE) works fine.
   const { isAvailable } = await import('../ai/gateway.ts');
   const providerProbe = resolvedCol.embeddingModel || undefined;
-  if (!isAvailable('embedding', providerProbe)) {
+  // Image/both/unified routing embeds via the MULTIMODAL provider, not the
+  // text provider — so a multimodal-only install (text provider absent) must
+  // still reach the multimodal branch below. Probe the multimodal provider
+  // explicitly and only short-circuit when neither the text provider nor (for
+  // multimodal-routed queries) the multimodal provider is reachable. Without
+  // this guard a multimodal-only install would fall to keyword-only here and
+  // never run the image/unified vector path.
+  const multimodalProviderProbe =
+    cfgForColumn?.embedding_multimodal_model ?? 'voyage:voyage-multimodal-3';
+  // The LLM intent tie-break (below) can escalate a regex-'text' query to
+  // 'image'/'both'; account for that possibility so an ambiguous query on a
+  // multimodal-only install still reaches the multimodal branch.
+  const mayEscalateToMultimodal =
+    earlyModality === 'text' &&
+    resolvedMode.cross_modal_llm_intent &&
+    isAmbiguousModalityQuery(query);
+  const willTryMultimodal =
+    (resolvedMode.unified_multimodal === true ||
+      earlyModality === 'image' ||
+      earlyModality === 'both' ||
+      mayEscalateToMultimodal) &&
+    isAvailable('embedding', multimodalProviderProbe);
+  if (!isAvailable('embedding', providerProbe) && !willTryMultimodal) {
     // v0.43 — fuse the relational arm with keyword so typed-edge answers
     // survive on the no-embedding-provider path (the relational win is most
     // valuable exactly when vector is unavailable). The title arm fuses here
@@ -1267,7 +1289,10 @@ export async function hybridSearch(
   if (unifiedRouting) {
     try {
       const { isAvailable: aiIsAvailable, embedQueryMultimodal } = await import('../ai/gateway.ts');
-      if (!aiIsAvailable('embedding')) {
+      // Probe the MULTIMODAL provider, not the global default — on a
+      // multimodal-only install the global default (text) is absent but the
+      // multimodal provider is configured, and unified routing embeds via it.
+      if (!aiIsAvailable('embedding', multimodalProviderProbe)) {
         throw new Error('gateway not configured for embedding — unified multimodal would also fail');
       }
       const unifiedEmbedding = await embedQueryMultimodal(query);
@@ -1302,7 +1327,10 @@ export async function hybridSearch(
     // OR the embed throws, log a structured warning and fall through to text.
     try {
       const { isAvailable: aiIsAvailable, embedQueryMultimodal } = await import('../ai/gateway.ts');
-      if (!aiIsAvailable('embedding')) {
+      // Probe the MULTIMODAL provider, not the global default — the image side
+      // embeds via the multimodal model, which may be configured even when the
+      // text/global-default embedding provider is absent (multimodal-only).
+      if (!aiIsAvailable('embedding', multimodalProviderProbe)) {
         throw new Error('gateway not configured for embedding — multimodal would also fail');
       }
       const imageEmbedding = await embedQueryMultimodal(query);
diff --git a/test/search-multimodal-no-embed.serial.test.ts b/test/search-multimodal-no-embed.serial.test.ts
new file mode 100644
index 000000000..ae031c36f
--- /dev/null
+++ b/test/search-multimodal-no-embed.serial.test.ts
@@ -0,0 +1,120 @@
+// Regression: no-embedding-provider early-return must be multimodal-aware.
+//
+// On a multimodal-only install (text embedding provider ABSENT, a multimodal
+// provider such as Voyage multimodal-3 PRESENT), hybridSearch's
+// no-embedding-provider short-circuit used to probe ONLY the text column's
+// provider. Since that provider is unreachable, search returned to the
+// keyword-only path (vector_enabled:false) BEFORE the image/unified vector
+// routing below ever ran — so image and unified queries silently degraded to
+// keyword search even though a usable multimodal vector path existed.
+//
+// The fix adds a `willTryMultimodal` guard that also probes the multimodal
+// provider so the early-return does not fire when multimodal vectoring is
+// still possible. These tests assert that the multimodal (Voyage) embedding
+// endpoint is actually reached on a text-provider-absent install.
+
+import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, test } from 'bun:test';
+import { PGLiteEngine } from '../src/core/pglite-engine.ts';
+import { resetPgliteState } from './helpers/reset-pglite.ts';
+import { configureGateway, resetGateway } from '../src/core/ai/gateway.ts';
+import { hybridSearch } from '../src/core/search/hybrid.ts';
+
+let engine: PGLiteEngine;
+let fetchHandler: ((url: string, init: RequestInit) => Promise<Response>) | null = null;
+const origFetch = globalThis.fetch;
+
+beforeAll(async () => {
+  engine = new PGLiteEngine();
+  await engine.connect({});
+  await engine.initSchema();
+});
+
+afterAll(async () => {
+  await engine.disconnect();
+});
+
+beforeEach(async () => {
+  await resetPgliteState(engine);
+  globalThis.fetch = (async (url: string | URL | Request, init?: RequestInit) => {
+    if (!fetchHandler) throw new Error('no fetch handler');
+    return fetchHandler(typeof url === 'string' ? url : url.toString(), init ?? {});
+  }) as typeof fetch;
+
+  // Multimodal-only install: a text embedding model is *configured* but its
+  // required auth env (OPENAI_API_KEY) is ABSENT, so the text provider is
+  // unreachable. The multimodal provider (Voyage) IS reachable (VOYAGE_API_KEY
+  // present). This is exactly the install shape the fix targets.
+  configureGateway({
+    embedding_model: 'openai:text-embedding-3-large',
+    embedding_dimensions: 1536,
+    embedding_multimodal_model: 'voyage:voyage-multimodal-3',
+    env: { VOYAGE_API_KEY: 'test' },
+  });
+});
+
+afterEach(() => {
+  globalThis.fetch = origFetch;
+  resetGateway();
+  fetchHandler = null;
+});
+
+describe('multimodal-only install: no-embedding early-return is multimodal-aware', () => {
+  test('image query still reaches the multimodal vector path (does not short-circuit to keyword)', async () => {
+    let voyageCalled = 0;
+    let openaiCalled = 0;
+    fetchHandler = async (url) => {
+      if (url.includes('multimodalembeddings')) {
+        voyageCalled++;
+        return new Response(JSON.stringify({
+          data: [{ embedding: Array.from({ length: 1024 }, () => 0.1), index: 0 }],
+        }), { status: 200 });
+      }
+      if (url.includes('api.openai.com') && url.includes('embeddings')) {
+        openaiCalled++;
+      }
+      return new Response(JSON.stringify({
+        data: [{ embedding: Array.from({ length: 1536 }, () => 0.1), index: 0 }],
+      }), { status: 200 });
+    };
+
+    const results = await hybridSearch(engine, 'a photo of a red bicycle', {
+      limit: 5,
+      crossModal: 'image',
+    });
+
+    // Pre-fix: the text-provider probe failed → early-return → Voyage never
+    // called. Post-fix: the image branch runs and embeds via the multimodal
+    // (Voyage) provider.
+    expect(voyageCalled).toBeGreaterThanOrEqual(1);
+    // The unreachable text provider must never have been dialed.
+    expect(openaiCalled).toBe(0);
+    expect(Array.isArray(results)).toBe(true);
+  });
+
+  test('unified_multimodal routing reaches the multimodal vector path on a text-provider-absent install', async () => {
+    await engine.setConfig('search.unified_multimodal', 'true');
+    let voyageCalled = 0;
+    let openaiCalled = 0;
+    fetchHandler = async (url) => {
+      if (url.includes('multimodalembeddings')) {
+        voyageCalled++;
+        return new Response(JSON.stringify({
+          data: [{ embedding: Array.from({ length: 1024 }, () => 0.1), index: 0 }],
+        }), { status: 200 });
+      }
+      if (url.includes('api.openai.com') && url.includes('embeddings')) {
+        openaiCalled++;
+      }
+      return new Response(JSON.stringify({
+        data: [{ embedding: Array.from({ length: 1536 }, () => 0.1), index: 0 }],
+      }), { status: 200 });
+    };
+
+    await hybridSearch(engine, 'totally text query', { limit: 5 });
+
+    // Unified routing forces the multimodal endpoint even for a text-shaped
+    // query; pre-fix the early-return fired first and Voyage was never called.
+    expect(voyageCalled).toBeGreaterThanOrEqual(1);
+    expect(openaiCalled).toBe(0);
+  });
+});