Perplexity for WhatsApp business
Sonar models — answers grounded in live web search with citations.
- No free tier
- Cost: Low–Medium
- Speed: Moderate
- Best for: Web-grounded answers
It's a WhatsApp bot powered by Perplexity's Sonar models — which pull answers from live web search results with citations. With ChatMitra you bring your Perplexity API key — setup takes about 5 minutes.
What it looks like in real businesses
Four chats from real industries, all using Perplexity (sonar) inside ChatMitra. Mix of English, Hindi, and Hinglish — the way customers actually type.
Picked by ChatMitra customers in travel, finance, and news where 'last week's data' isn't acceptable.
In simple terms: Perplexity doesn't try to be everything — it's strong at one specific thing: replies grounded in live web search. If your customers ask about today's events, current prices, or anything where 'last week' is too old, Sonar is the pick.
Not 100% sure Perplexity is right for you?
That's okay — you can switch any time inside ChatMitra. Quick orientation:
- • If cost is your main concern, Groq or DeepSeek are worth a look
- • If top-shelf quality matters more, OpenAI or Anthropic are the usual picks
- • If you want balance, Gemini sits well in the middle
Still unsure? Start with Perplexity — switching later is one click inside ChatMitra without rebuilding your bot.
What is Perplexity, really?
Perplexity doesn't try to be everything — it's strong at one specific thing: replies grounded in live web search results.
Perplexity is a US AI search company founded in 2022, known for the Sonar family. If your business needs replies that include current information (today's news, this week's prices, latest schedules), Sonar's web grounding is what you want — most other models just guess from training data.
Perplexity models in 2026
The model with the green badge is what we usually recommend for everyday WhatsApp business chats. Step up only if you actually need it.
Pricing in USD as published on Perplexity's pricing page. INR figures are approximate. Verified on 2026-04-30.
Source: official model docs · official pricing page
What will Perplexity cost my business?
Three rough volumes, costs in approximate INR. Your actual number will vary — see assumptions below.
- • Avg 15–20 messages per conversation
- • Avg 50–100 tokens per message
- • Pricing as published by Perplexity on 2026-04-30 — may change. Source: docs.perplexity.ai/docs/getting-started/pricing
Best for these businesses
Pick Perplexity when your customers ask about things that change — today's news, this week's prices, current availability. Skip it for static FAQ replies.
- News, media, financial services where current information matters
- Travel agencies — flight schedules, hotel availability, weather
- Real estate — current listings, market prices
- Anywhere customers ask 'what's happening today / this week'
- Static FAQ-style chat — you're paying for web search you won't use
- High-volume routine queries — cheaper providers handle these better
Sonar is brilliant when answers depend on fresh information. For everyday 'is this in stock' or 'what are your hours' queries, you're paying for web search you don't need. Use it where it shines, not as a default.
How to get your Perplexity API key
Whole flow takes about 5 minutes. Mockups below are deliberately generic — Perplexity's dashboard may look slightly different by the time you read this, but the steps stay roughly the same.
1. Create your Perplexity account
Sign up using your business email. If you already have a Perplexity login (or a parent-product login), the same one usually works.
www.perplexity.ai/settings/api2. Add a payment method
Perplexity doesn't have a permanent free tier on the API, so you'll need a card before you can create a key. Most stores top up with $5–10 — that's enough for testing and the first few hundred chats.
3. Open the API keys section
In the dashboard sidebar (or your profile menu), find "API keys". Click into it.
www.perplexity.ai/settings/api4. Create a new secret key
Click "Create new key", give it a name like "ChatMitra production". Copy the key the moment it appears — most providers won't show it again.
5. Paste it into ChatMitra
Inside the AI Chatbot wizard (Step 2 — Pick your AI), select Perplexity, paste the key. ChatMitra validates it on the spot. Green tick = ready.
UI may change slightly as Perplexity updates their dashboard. The flow stays roughly the same — sign up, add a payment method (if needed), find the API keys section, create a key, copy it.
Set up Perplexity in ChatMitra (about 5 minutes)
Once you've copied your API key from Perplexity, the rest happens inside ChatMitra. Same wizard you'd use for any other provider — just pre-filled for Perplexity.
Pick Perplexity as your AI
In the ChatMitra AI Chatbot wizard, Step 2 shows the provider grid. Click Perplexity's tile, paste the API key you just copied. ChatMitra checks the key right then — green tick = ready.
Perplexity SelectedPick a model
ChatMitra auto-selects sonar as the default — that's our pick for everyday WhatsApp business chat. You can override if you want a different one.
Write the bot's personality
Tell ChatMitra about your business — name, industry, a one-line description. Then write the personality prompt yourself, or click Generate with AI and tweak the draft. Perplexity reads this prompt before every reply.
Add a fallback (optional, recommended)
Add up to 3 backup providers. If Perplexity rate-limits or has an outage, ChatMitra automatically switches to the backup — your customers don't see an error. Most teams add one of Openai or Gemini here.
Test, then activate
Built-in chat simulator lets you message your bot before any real customer does. Try a tricky question. When it looks right, hit Activate — and the bot starts answering on the WhatsApp number you've already connected to ChatMitra.
Worried about getting locked in? You can change AI providers any time inside ChatMitra. The bot's personality, conversation history, and customer data stay exactly where they are — only the underlying AI changes. Try Perplexity first, switch later if something better fits.
Perplexity for Indian SMBs — pros & cons
What's good
- Replies include real-time web search results — great for current-info queries
- Citations included — customers can verify the source if your business needs that
- Sonar Reasoning Pro at $2 / $8 is competitive with OpenAI's o3 ($2 / $8) but with web grounding included
What to watch out for
- Overkill (and pricier) for static FAQ replies
- No permanent free tier
- Sonar Deep Research has hidden costs — reasoning tokens + search query fees stack up
Compare with other providers
Which is better — Perplexity or OpenAI? It depends what you need.
- Web-grounded answers → pick Perplexity
- High-accuracy replies → pick OpenAI
- All-rounder + free tier → pick Google Gemini
Each label is what the provider does best. Match it to your priority — that's usually the right pick.
Top picks by category:
- OpenAI — best for accuracy and complex replies
- Groq — best for cost and high-volume chat
- Google Gemini — best balanced choice for most Indian SMBs
- Perplexity — sonar models — answers grounded in live web search with citations
Direct comparisons:
Or explore other ChatMitra options:
Sources & references
Every model name, context window, and price on this page is copied from Perplexity's own public pages on 2026-04-30. Providers update pricing fairly often — please double-check before you commit to a plan.
- Models & specs: docs.perplexity.ai/docs/getting-started/models
- Pricing: docs.perplexity.ai/docs/getting-started/pricing
- Get your API key: www.perplexity.ai/settings/api
Try Perplexity on your WhatsApp in 5 minutes
15 days free. No card. Switch providers any time without rebuilding your bot.
Frequently Asked Questions
When should I pick Perplexity over OpenAI?
Pick Perplexity when your customers ask about current information — today's news, current prices, this week's schedule. Sonar pulls from live web search. For static FAQ replies, OpenAI / Gemini are cheaper and equally good.
How much does a Perplexity WhatsApp chatbot cost?
On base Sonar at $1 / $1 per 1M, expect ₹400–₹2,500 / month for a small Indian business doing 100–10,000 chats. Sonar Pro and Deep Research are 3–10× more, depending on usage.
Are citations included in replies?
Yes — Sonar replies include source citations. Citation tokens for standard Sonar and Sonar Pro are no longer billed in 2026, so they're effectively free.
Which Perplexity model should I pick?
Base Sonar is the right default. Step up to Sonar Pro for more complex queries; use Reasoning models only when the question genuinely needs step-by-step thinking.
Does Perplexity handle Hindi?
Yes — Sonar handles Hindi and Hinglish reasonably well, and it can search Hindi-language web pages too. For pure-Hindi customer bases, test before committing.