docs: update OpenRouter documentation to reflect native embedding support and clarify plugin configurations

Author: standujar

plugin-registry/knowledge/contextual-embeddings.mdx

@@ -77,18 +77,17 @@ GOOGLE_API_KEY=your-key      # If using Google
 **Important**: Embeddings always use the model configured in `useModel(TEXT_EMBEDDING)` from your agent setup. Do NOT try to mix different embedding models - all your documents must use the same embedding model for consistency.
 </Warning>
 
-### Recommended Setup: OpenRouter with Separate Embedding Provider
+### OpenRouter Standalone Setup
 
-Since OpenRouter doesn't support embeddings, you need a separate embedding provider:
+OpenRouter now supports embeddings natively with multiple models (`text-embedding-3-large`, `qwen3-embedding`, `gemini-embedding`, `mistral-embed`):
 
 <Tabs>
-  <Tab title="OpenRouter + OpenAI">
+  <Tab title="OpenRouter Only">
     ```typescript title="character.ts"
     export const character = {
       name: 'MyAgent',
       plugins: [
-        '@elizaos/plugin-openrouter',  // For text generation
-        '@elizaos/plugin-openai',       // For embeddings
+        '@elizaos/plugin-openrouter',   // Handles both text and embeddings
         '@elizaos/plugin-knowledge',    // Knowledge plugin
       ],
     };
@@ -98,22 +97,18 @@ Since OpenRouter doesn't support embeddings, you need a separate embedding provi
     # Enable contextual embeddings
     CTX_KNOWLEDGE_ENABLED=true
 
-    # Text generation (for context enrichment)
-    TEXT_PROVIDER=openrouter
-    TEXT_MODEL=anthropic/claude-3-haiku
+    # OpenRouter handles both text generation and embeddings
     OPENROUTER_API_KEY=your-openrouter-key
-
-    # Embeddings (automatically used)
-    OPENAI_API_KEY=your-openai-key
+    OPENROUTER_EMBEDDING_MODEL=openai/text-embedding-3-large  # Optional
     ```
   </Tab>
-  <Tab title="OpenRouter + Google">
+  <Tab title="OpenRouter + Local Fallback">
     ```typescript title="character.ts"
     export const character = {
       name: 'MyAgent',
       plugins: [
-        '@elizaos/plugin-openrouter',  // For text generation
-        '@elizaos/plugin-google',       // For embeddings
+        '@elizaos/plugin-openrouter',  // Cloud text & embeddings
+        '@elizaos/plugin-ollama',       // Offline fallback
         '@elizaos/plugin-knowledge',    // Knowledge plugin
       ],
     };
@@ -123,13 +118,11 @@ Since OpenRouter doesn't support embeddings, you need a separate embedding provi
     # Enable contextual embeddings
     CTX_KNOWLEDGE_ENABLED=true
 
-    # Text generation (for context enrichment)
-    TEXT_PROVIDER=openrouter
-    TEXT_MODEL=anthropic/claude-3-haiku
+    # OpenRouter for cloud
     OPENROUTER_API_KEY=your-openrouter-key
 
-    # Embeddings (Google will be used automatically)
-    GOOGLE_API_KEY=your-google-key
+    # Ollama as fallback for offline use
+    OLLAMA_API_ENDPOINT=http://localhost:11434/api
     ```
   </Tab>
 </Tabs>

plugin-registry/knowledge/quick-start.mdx

@@ -166,7 +166,6 @@ export const character = {
   name: 'MyAgent',
   plugins: [
     '@elizaos/plugin-openrouter',
-    '@elizaos/plugin-openai', // ← Make sure you have this as openrouter doesn't support embeddings
     '@elizaos/plugin-knowledge', // ← Add this line
     // ... your other plugins
   ],
@@ -176,11 +175,11 @@ export const character = {
 
 ```env title=".env"
 OPENROUTER_API_KEY=your-openrouter-api-key
-OPENAI_API_KEY=your-openai-api-key
+OPENROUTER_EMBEDDING_MODEL=openai/text-embedding-3-large  # Optional: specify embedding model
 ```
 
 <Note>
-The plugin automatically uses OpenAI embeddings even when using OpenRouter for text generation.
+OpenRouter now supports embeddings natively with multiple models: `text-embedding-3-large`, `qwen3-embedding`, `gemini-embedding`, `mistral-embed`.
 </Note>
 
 ## <Icon icon="question" /> FAQ

plugin-registry/llm.mdx

@@ -31,11 +31,11 @@ Not all LLM plugins support all model types. Here's what each can do:
 | Anthropic | ✅ | ❌ | ✅ | ❌ |
 | Google GenAI | ✅ | ✅ | ✅ | ❌ |
 | Ollama | ✅ | ✅ | ✅ | ✅ |
-| OpenRouter | ✅ | ❌ | ✅ | ❌ |
+| OpenRouter | ✅ | ✅ | ✅ | ❌ |
 
 **Key Points:**
-- 🌟 **OpenAI & Google GenAI** = Do everything (jack of all trades)
-- 💬 **Anthropic & OpenRouter** = Amazing at chat, need help with embeddings
+- 🌟 **OpenAI, Google GenAI & OpenRouter** = Do everything (jack of all trades)
+- 💬 **Anthropic** = Amazing at chat, needs a fallback for embeddings
 - 🏠 **Ollama** = Your local hero - does almost everything, no internet needed!
 
 ## Plugin Loading Order
@@ -49,9 +49,9 @@ plugins: [
 
   // Text-only plugins (no embedding support)
   ...(process.env.ANTHROPIC_API_KEY?.trim() ? ['@elizaos/plugin-anthropic'] : []),
-  ...(process.env.OPENROUTER_API_KEY?.trim() ? ['@elizaos/plugin-openrouter'] : []),
 
-  // Embedding-capable plugins (optional, based on available credentials)
+  // Embedding-capable plugins
+  ...(process.env.OPENROUTER_API_KEY?.trim() ? ['@elizaos/plugin-openrouter'] : []),
   ...(process.env.OPENAI_API_KEY?.trim() ? ['@elizaos/plugin-openai'] : []),
   ...(process.env.GOOGLE_GENERATIVE_AI_API_KEY?.trim() ? ['@elizaos/plugin-google-genai'] : []),
 
@@ -64,9 +64,9 @@ plugins: [
 
 Think of it like choosing team players - you pick specialists first, then all-rounders:
 
-1. **Anthropic & OpenRouter go first** - They're specialists! They're great at text generation but can't do embeddings. By loading them first, they get priority for text tasks.
+1. **Anthropic goes first** - It's a specialist! Great at text generation but can't do embeddings. By loading it first, it gets priority for text tasks.
 
-2. **OpenAI & Google GenAI come next** - These are the all-rounders! They can do everything: text generation, embeddings, and structured output. They act as fallbacks for what the specialists can't do.
+2. **OpenRouter, OpenAI & Google GenAI come next** - These are the all-rounders! They can do everything: text generation, embeddings, and structured output. They act as fallbacks for what Anthropic can't do (embeddings).
 
 3. **Ollama comes last** - This is your local backup player! It supports almost everything (text, embeddings, objects) and runs on your computer. Perfect when cloud services aren't available.
 
@@ -165,12 +165,21 @@ elizaOS automatically finds another plugin that CAN do embeddings!
 }
 ```
 
-#### OpenRouter + Local Embeddings
+#### OpenRouter Standalone
+```json
+{
+  "plugins": [
+    "@elizaos/plugin-openrouter"  // Handles text and embeddings
+  ]
+}
+```
+
+#### OpenRouter + Local Fallback
 ```json
 {
   "plugins": [
-    "@elizaos/plugin-openrouter",  // Cloud text generation
-    "@elizaos/plugin-ollama"        // Local embeddings
+    "@elizaos/plugin-openrouter",  // Cloud text & embeddings
+    "@elizaos/plugin-ollama"        // Offline fallback
   ]
 }
 ```

plugin-registry/llm/openrouter.mdx

@@ -43,8 +43,7 @@ OPENROUTER_IMAGE_MODEL=anthropic/claude-3-5-sonnet           # For vision tasks
 {
   "name": "MyAgent",
   "plugins": [
-    "@elizaos/plugin-openrouter",
-    "@elizaos/plugin-ollama"  // For embeddings
+    "@elizaos/plugin-openrouter"
   ]
 }
 ```
@@ -54,20 +53,22 @@ OPENROUTER_IMAGE_MODEL=anthropic/claude-3-5-sonnet           # For vision tasks
 | Operation | Support | Notes |
 |-----------|---------|-------|
 | TEXT_GENERATION | ✅ | All available models |
-| EMBEDDING | ❌ | Use fallback plugin |
+| EMBEDDING | ✅ | Multiple embedding models available |
 | OBJECT_GENERATION | ✅ | Model dependent |
 
-## Important: Embedding Fallback
+## Embedding Models
 
-OpenRouter doesn't provide embedding endpoints, so include a fallback:
+OpenRouter now provides embedding endpoints with multiple models:
 
-```json
-{
-  "plugins": [
-    "@elizaos/plugin-openrouter",  // Text generation
-    "@elizaos/plugin-openai"        // Embeddings
-  ]
-}
+- `text-embedding-3-large` (OpenAI via OpenRouter)
+- `qwen3-embedding` (Qwen)
+- `gemini-embedding` (Google)
+- `mistral-embed` (Mistral)
+
+Configure embedding model:
+
+```bash
+OPENROUTER_EMBEDDING_MODEL=openai/text-embedding-3-large
 ```
 
 ## Model Configuration