docs: Add Mistral and Moonshot provider documentation

Add complete documentation for Mistral and Moonshot LLM providers:

- Add provider cards with authentication and vision support details
- Add configuration sections with environment variables
- Add API usage examples for both providers
- Update architecture diagrams to include both providers
- Update provider lists in API reference
- Regenerate search index and sitemap

Signed-off-by: Eden Reich <eden.reich@gmail.com>

Author: edenreich

markdown/api-reference.mdx

@@ -73,7 +73,7 @@ Get a list of available models for a specific provider.
 GET /v1/models?provider={provider}
 ```
 
-where `{provider}` is one of: `openai`, `anthropic`, `cohere`, `groq`, `cloudflare`, `ollama`, `deepseek`.
+where `{provider}` is one of: `openai`, `anthropic`, `cohere`, `groq`, `cloudflare`, `ollama`, `deepseek`, `mistral`, `moonshot`.
 
 **Response**:
 
@@ -476,6 +476,7 @@ curl -X POST http://localhost:8080/v1/chat/completions \
 - Ollama (LLaVA, Llama 4, Llama 3.2 Vision)
 - Groq (vision models)
 - Mistral (Pixtral)
+- Moonshot (vision models)
 
 **Note:** When `ENABLE_VISION=false` (default), requests containing image content will be rejected even if the model supports vision. This is disabled by default for performance and security reasons.
 

markdown/architecture-overview.mdx

@@ -30,6 +30,8 @@ graph TD
     P --> H1["💬 Cohere"]
     P --> H2["🧠 Anthropic"]
     P --> H3["🐋 DeepSeek"]
+    P --> H4["🌟 Mistral"]
+    P --> H5["🌙 Moonshot"]
 
     %% Define styles
     classDef client fill:#9370DB,stroke:#333,stroke-width:1px,color:white;
@@ -41,7 +43,7 @@ graph TD
     class A client;
     class Auth auth;
     class IG1,IG2,IG3,P gateway;
-    class C,D,E,G,H1,H2,H3 provider;
+    class C,D,E,G,H1,H2,H3,H4,H5 provider;
 ```
 
 ## Kubernetes Setup
@@ -103,6 +105,8 @@ graph TD
             Ext5["💬 Cohere"]
             Ext6["🚀 Groq"]
             Ext7["🐋 DeepSeek"]
+            Ext8["🌟 Mistral"]
+            Ext9["🌙 Moonshot"]
         end
     end
 
@@ -121,7 +125,7 @@ graph TD
     class Pod1,Pod2,Pod3 pod;
     class Prometheus,Grafana monitoring;
     class SM monitor;
-    class Ext1,Ext2,Ext3,Ext4,Ext5,Ext6,Ext7 externalSvc;
+    class Ext1,Ext2,Ext3,Ext4,Ext5,Ext6,Ext7,Ext8,Ext9 externalSvc;
     class IG1,IG2,IG3,PG1,PG2,PG3 service;
     class InternalClients,InternalAgents internalClient;
     class ExternalProviders extProviders;

markdown/configuration.mdx

@@ -239,6 +239,32 @@ Configure access to various LLM providers. At minimum, you should configure the
   ]}
 />
 
+#### Mistral
+
+<ConfigTable
+  rows={[
+    {
+      variable: 'MISTRAL_API_URL',
+      description: 'Mistral AI API URL',
+      defaultValue: 'https://api.mistral.ai/v1',
+    },
+    { variable: 'MISTRAL_API_KEY', description: 'Mistral AI API Key', defaultValue: '""' },
+  ]}
+/>
+
+#### Moonshot
+
+<ConfigTable
+  rows={[
+    {
+      variable: 'MOONSHOT_API_URL',
+      description: 'Moonshot AI API URL',
+      defaultValue: 'https://api.moonshot.ai/v1',
+    },
+    { variable: 'MOONSHOT_API_KEY', description: 'Moonshot AI API Key', defaultValue: '""' },
+  ]}
+/>
+
 ### Model Context Protocol (MCP) Settings
 
 These settings control MCP integration for external tool access:
@@ -431,6 +457,8 @@ GOOGLE_API_URL=https://generativelanguage.googleapis.com/v1beta/openai
 GOOGLE_API_KEY=
 MISTRAL_API_URL=https://api.mistral.ai/v1
 MISTRAL_API_KEY=
+MOONSHOT_API_URL=https://api.moonshot.ai/v1
+MOONSHOT_API_KEY=
 ```
 
 ## Configuration Best Practices

markdown/supported-providers.mdx

@@ -102,12 +102,40 @@ The following LLM providers are currently supported:
   </div>
 </div>
 
+<div className="border p-4 rounded-md">
+  <h3>Google</h3>
+  <p>Access Google's Gemini models for text generation and understanding.</p>
+  <div>
+    <strong>Authentication:</strong> Bearer Token
+  </div>
+  <div>
+    <strong>Default URL:</strong> https://generativelanguage.googleapis.com/v1
+  </div>
+  <div>
+    <strong>Vision Support:</strong> ✅ Yes (Gemini 2.5)
+  </div>
+</div>
+
+<div className="border p-4 rounded-md">
+  <h3>Mistral</h3>
+  <p>Access Mistral AI's models including vision-capable Pixtral.</p>
+  <div>
+    <strong>Authentication:</strong> Bearer Token
+  </div>
+  <div>
+    <strong>Default URL:</strong> https://api.mistral.ai/v1
+  </div>
+  <div>
+    <strong>Vision Support:</strong> ✅ Yes (Pixtral)
+  </div>
+</div>
+
   <div className="border p-4 rounded-md">
-    <h3>Google</h3>
-    <p>Access Google's Gemini models for text generation and understanding.</p>
+    <h3>Moonshot</h3>
+    <p>Use Moonshot AI's models for natural language and vision tasks.</p>
     <div><strong>Authentication:</strong> Bearer Token</div>
-    <div><strong>Default URL:</strong> https://generativelanguage.googleapis.com/v1</div>
-    <div><strong>Vision Support:</strong> ✅ Yes (Gemini 2.5)</div>
+    <div><strong>Default URL:</strong> https://api.moonshot.ai/v1</div>
+    <div><strong>Vision Support:</strong> ✅ Yes</div>
   </div>
 </div>
 
@@ -130,6 +158,7 @@ ENABLE_VISION=true
 - **Ollama**: LLaVA, Llama 4, Llama 3.2 Vision
 - **Groq**: Vision models
 - **Mistral**: Pixtral
+- **Moonshot**: Vision models
 
 ### Example Vision Request
 
@@ -167,7 +196,7 @@ Each provider requires specific configuration through environment variables:
 - `PROVIDER_API_URL`: The base URL for the provider's API
 - `PROVIDER_API_KEY`: The authentication key for the provider
 
-Replace "PROVIDER" with the provider name (uppercase): OPENAI, ANTHROPIC, COHERE, GROQ, CLOUDFLARE, OLLAMA, GOOGLE, DEEPSEEK.
+Replace "PROVIDER" with the provider name (uppercase): OPENAI, ANTHROPIC, COHERE, GROQ, CLOUDFLARE, OLLAMA, GOOGLE, DEEPSEEK, MISTRAL, MOONSHOT.
 
 ### API Endpoints
 
@@ -402,3 +431,47 @@ curl -X POST http://localhost:8080/v1/chat/completions?provider=google \
     ]
   }'
 ```
+
+### Mistral Provider
+
+Generate content with Mistral AI models:
+
+```bash
+curl -X POST http://localhost:8080/v1/chat/completions?provider=mistral \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "mistral-large-latest",
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful assistant."
+      },
+      {
+        "role": "user",
+        "content": "Explain the differences between supervised and unsupervised learning."
+      }
+    ]
+  }'
+```
+
+### Moonshot Provider
+
+Generate content with Moonshot AI models:
+
+```bash
+curl -X POST http://localhost:8080/v1/chat/completions?provider=moonshot \
+  -H "Content-Type: application/json" \
+  -d '{
+    "model": "moonshot-v1-8k",
+    "messages": [
+      {
+        "role": "system",
+        "content": "You are a helpful assistant."
+      },
+      {
+        "role": "user",
+        "content": "What are the key principles of clean code?"
+      }
+    ]
+  }'
+```

public/search-index.json

@@ -20,13 +20,13 @@
   </url>
   <url>
     <loc>https://docs.inference-gateway.com/api-reference</loc>
-    <lastmod>2025-11-15T21:47:42.264Z</lastmod>
+    <lastmod>2026-01-23T21:03:58.862Z</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.8</priority>
   </url>
   <url>
     <loc>https://docs.inference-gateway.com/architecture-overview</loc>
-    <lastmod>2025-04-15T17:06:58.875Z</lastmod>
+    <lastmod>2026-01-23T21:04:37.908Z</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.8</priority>
   </url>
@@ -44,13 +44,13 @@
   </url>
   <url>
     <loc>https://docs.inference-gateway.com/configuration</loc>
-    <lastmod>2025-11-21T18:09:56.661Z</lastmod>
+    <lastmod>2026-01-23T21:03:37.726Z</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.8</priority>
   </url>
   <url>
     <loc>https://docs.inference-gateway.com/deployment</loc>
-    <lastmod>2026-01-23T20:44:34.331Z</lastmod>
+    <lastmod>2026-01-23T20:51:19.657Z</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.8</priority>
   </url>
@@ -92,7 +92,7 @@
   </url>
   <url>
     <loc>https://docs.inference-gateway.com/supported-providers</loc>
-    <lastmod>2025-11-15T21:28:17.983Z</lastmod>
+    <lastmod>2026-01-23T21:05:10.589Z</lastmod>
     <changefreq>monthly</changefreq>
     <priority>0.8</priority>
   </url>