feat: add proxy handler docs

api-reference/inference-api/gateway-for-other-apis.mdx

@@ -332,6 +332,47 @@ const response = await portkey.delete('/collections/my-collection');
 </Tab>
 </Tabs>
 
+## Configs work as usual
+
+Pass an `x-portkey-config` header (or a saved config ID) to apply **fallback**, **loadbalance**, or **conditional** routing—exactly like on `/chat/completions`.
+
+```sh
+curl https://api.portkey.ai/v1/rerank \
+  -H "Content-Type: application/json" \
+  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
+  -H 'x-portkey-config: {
+    "strategy": { "mode": "fallback" },
+    "targets": [
+      { "provider": "@cohere-prod" },
+      { "provider": "@cohere-backup" }
+    ]
+  }' \
+  -d '{ "model": "rerank-english-v2.0", "query": "...", "documents": ["..."] }'
+```
+
+Retries, caching, and guardrails apply the same way.
+
+## Force the proxy on a built-in route
+
+Portkey handles `/chat/completions`, `/embeddings`, and other built-in routes with dedicated logic. To bypass that and send the request through untouched, prefix the path with `/v1/proxy/`:
+
+```sh
+curl https://api.portkey.ai/v1/proxy/chat/completions \
+  -H "Content-Type: application/json" \
+  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
+  -H "x-portkey-provider: openai" \
+  -H "Authorization: Bearer $OPENAI_API_KEY" \
+  -d '{"model":"gpt-4.1-mini","messages":[{"role":"user","content":"Hello"}]}'
+```
+
+Use this only when raw passthrough is required.
+
+## Pricing and analytics
+
+- **Token counts** in the response come straight from the provider.
+- **Cost tracking** works when Portkey knows the model's pricing. Common provider + model combinations are recognized automatically.
+- For **custom models** or unusual endpoints, add the pricing in your Portkey dashboard so cost numbers stay accurate.
+
 ## End-to-end Example
 
 <Accordion title="Cohere Rerank Integration">

product/ai-gateway.mdx

@@ -67,6 +67,10 @@ description: The world's fastest AI Gateway with advanced routing & integrated G
   <Card title="Custom Hosts" href="/product/ai-gateway/custom-hosts">
     Route requests to privately hosted or local models using custom host URLs
   </Card>
+
+  <Card title="Gateway to other APIs" href="/api-reference/inference-api/gateway-for-other-apis">
+    Call rerank, video, listen, and other provider paths through https://api.portkey.ai/v1/... with the same configs and logging as unified routes
+  </Card>
 </CardGroup>