From e243c41234adc241b8ce84af9715f46eba46cd31 Mon Sep 17 00:00:00 2001
From: Bhishmendra Mahala <bhishmendramahala@Bhishmendra--MacBook-Air.local>
Date: Wed, 25 Feb 2026 15:18:43 +0530
Subject: [PATCH 1/2] docs: add Perplexity AI as native Responses API provider

---
 product/ai-gateway/responses-api.mdx | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/product/ai-gateway/responses-api.mdx b/product/ai-gateway/responses-api.mdx
index 4011baba..17d64c61 100644
--- a/product/ai-gateway/responses-api.mdx
+++ b/product/ai-gateway/responses-api.mdx
@@ -764,7 +764,7 @@ Portkey handles the Responses API in two ways depending on the provider:
 
 This translation is transparent — the response format is identical regardless of which provider handles the request.
 
-**Native providers:** OpenAI, Azure OpenAI, Grok (x.ai), Groq, OpenRouter, Azure AI
+**Native providers:** OpenAI, Azure OpenAI, Grok (x.ai), Groq, OpenRouter, Azure AI, Perplexity AI 
 
 **Adapter providers:** Anthropic, Google Gemini, Google Vertex AI, AWS Bedrock, Mistral AI, Together AI, and [all other providers](/integrations)
 

From cfb9d6ee4c652e525f5816ac548cbb62c2b1a43a Mon Sep 17 00:00:00 2001
From: Bhishmendra Mahala <bhishmendramahala@Bhishmendra--MacBook-Air.local>
Date: Fri, 13 Mar 2026 16:54:18 +0530
Subject: [PATCH 2/2] docs: add Responses API section and examples to
 Perplexity integration

Made-with: Cursor
---
 integrations/llms/perplexity-ai.mdx | 50 +++++++++++++++++++++++++++++
 1 file changed, 50 insertions(+)

diff --git a/integrations/llms/perplexity-ai.mdx b/integrations/llms/perplexity-ai.mdx
index c8eb026a..27e32a7a 100644
--- a/integrations/llms/perplexity-ai.mdx
+++ b/integrations/llms/perplexity-ai.mdx
@@ -117,6 +117,56 @@ Before making requests, add Perplexity AI to your Model Catalog:
 
 ---
 
+## Responses API
+
+Perplexity AI is a **native Responses API provider** on Portkey — requests are sent directly to Perplexity's Responses API endpoint. You can use the same [Responses API](/product/ai-gateway/responses-api) format with `@perplexity-ai` models. This is available on Portkey's AI Gateway (cloud and self-hosted).
+
+<CodeGroup>
+
+```python Python
+from portkey_ai import Portkey
+
+portkey = Portkey(api_key="PORTKEY_API_KEY")
+
+response = portkey.responses.create(
+    model="@perplexity-ai/sonar",
+    input="What are the latest developments in AI?"
+)
+
+print(response.output_text)
+```
+
+```javascript JavaScript
+import Portkey from 'portkey-ai';
+
+const portkey = new Portkey({ apiKey: "PORTKEY_API_KEY" });
+
+const response = await portkey.responses.create({
+    model: "@perplexity-ai/sonar",
+    input: "What are the latest developments in AI?"
+});
+
+console.log(response.output_text);
+```
+
+```sh cURL
+curl https://api.portkey.ai/v1/responses \
+  -H "Content-Type: application/json" \
+  -H "x-portkey-api-key: $PORTKEY_API_KEY" \
+  -d '{
+    "model": "@perplexity-ai/sonar",
+    "input": "What are the latest developments in AI?"
+  }'
+```
+
+</CodeGroup>
+
+<Card title="Responses API reference" icon="code" href="/product/ai-gateway/responses-api">
+  Full Responses API docs — streaming, tools, instructions, and more
+</Card>
+
+---
+
 ## Perplexity AI Capabilities
 
 ### Citations