Perplexity logo

Perplexity

Access Perplexity models through Orq.ai for search-grounded chat, reasoning, research, and other web-connected AI workloads through one API.

3 models · 7 direct routes · 1 region

Direct regions:

Global

Loading pricing…

Role

Model creator · Inference provider

HQ

San Francisco, California

Role

Model creator · Inference provider

HQ

San Francisco, California

Direct API routes

3 models · 7 direct routes · 1 region

Global

Zero data retention

Not confirmed

Capabilities

Vision

Chat

Partner routes

Munito

1 routes

EU

ZDR on 1 of 1

Access Perplexity through Orq.ai’s AI Router

Perplexity is a search-focused AI provider that combines language models with web retrieval to produce grounded responses backed by current information and source citations. Its APIs are particularly suited to research, question answering, and workflows where responses need access to information beyond a model’s static training data.

Perplexity models available on Orq.ai

Compare the Perplexity models currently available through Orq.ai, including their supported capabilities, context windows, pricing, and regional availability.

3

models · newest first · base prices from this provider

Model
Input types
Region
ZDR
Input price
Output price
Intelligence
Context (tokens)
Release date
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Model
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Model
Select up to 3 models using the checkboxes to compare
Loading models…

EU and ZDR reflect all listed model routes, including partners.

Why use Perplexity through Orq.ai?

Chat & search

Route Perplexity workloads through Orq.ai while applying routing, tracing, evaluations, budgets, and governance controls around each request.

Research

Route research-heavy workflows to Perplexity while comparing cost, latency, and quality with other models from a shared control layer.

Long-context analysis

Send workloads that need search and deeper analysis to Perplexity while routing simpler tasks to other providers where appropriate.

Pricing

Pricing varies by model, API, search configuration, token usage, and billing setup. Some workloads combine token charges with search fees; research, embeddings, and other APIs may have separate structures. Check Orq.ai and your Perplexity setup for current rates.

Works with

Perplexity models and APIs can be incorporated into supported Orq.ai workflows through available provider and API integrations. Compatibility depends on the model, search capability, endpoint, and integration configuration being used.

FAQs

Do I need a separate Perplexity account to use Perplexity through Orq.ai?

You can connect supported Perplexity credentials to Orq.ai or use other available access options depending on your workspace, plan, and region.

Can I route only some workflows to Perplexity and others to different providers?

Yes. Orq.ai lets you route different workloads to different providers, so you can use Perplexity for search-grounded research and current-information workloads while routing tasks that do not require web access elsewhere.

Does using Perplexity through Orq.ai add latency?

Orq.ai adds a routing layer between your application and the provider. End-to-end latency can also depend on search retrieval, model processing, and workflow configuration, and can be monitored through Orq.ai where supported.

Alternatives to Perplexity

Meta logo

Meta

Explore Meta-created models through Orq.ai. Direct pricing and route statistics use Meta-hosted routes; other hosting providers are listed separately.

Image generation

Speech

Vision

Reasoning

Chat

Google logo

Google

Explore Google-created models, including Gemini and Gemma, through Orq.ai. Direct pricing and route statistics on this page use Google AI; other hosts are listed separately.

Code

Image generation

Speech

Embeddings

Vision

Reasoning

Chat

inception logo

Inception

Access Inception’s Mercury diffusion language models through Orq.ai for fast reasoning, coding, agentic, and other latency-sensitive AI workloads.

Code

Vision

Reasoning

Chat

Anthropic logo

Anthropic

Access Anthropic’s Claude models through Orq.ai for reasoning, coding, vision, and agentic workflows through one API.

Vision

Reasoning

Chat

Take control of your AI