Perplexity
on Orq.ai
Access Perplexity models through Orq.ai for search-grounded chat, reasoning, research, and other web-connected AI workloads through one API.
Capabilities:
Chat
Reasoning
Models Supported:
sonar
sonar-deep-research
sonar-pro
sonar-reasoning-pro
...
Provider HQ:
San Francisco, California
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.
Model
Type
Context
Input / 1M
Output / 1M
sonar
chat
128K
$1.00
$1.00
sonar-deep-research
chat
128K
$2.00
$8.00
sonar-pro
chat
Vision
200K
$3.00
$15.00
Why use Perplexity through Orq.ai?
Capability | Provider | Direct | Through Orq.ai |
|---|---|---|---|
Chat & search | Perplexity models | Use supported Perplexity APIs directly for search-grounded chat, question answering, and research with citations. | Route Perplexity workloads through Orq.ai while applying routing, tracing, evals, budgets, and governance controls around each request. |
Research | Perplexity research capabilities | Use supported models and APIs for web research, source-backed analysis, and information gathering. | Route research-heavy workflows to Perplexity while comparing cost, latency, and quality with other models from a shared control layer. |
Long-context analysis | Perplexity models | Use supported models for workflows that combine retrieved web information with larger amounts of context and multi-step analysis. | Send workloads that need search and deeper analysis to Perplexity while routing simpler tasks to other providers where appropriate. |
Using Perplexity through Orq.ai lets teams add search-grounded reasoning and web research to a wider model stack while centralizing routing, observability, evaluations, and cost controls.
Pricing
Perplexity pricing varies by model, API, search configuration, token usage, and billing setup.
Some workloads combine token-based model charges with request-based search fees or other usage charges. Search, research, embeddings, and other API capabilities may use different pricing structures.
You can connect supported Perplexity credentials to Orq.ai or use other available access options depending on your workspace configuration. Check Orq.ai and your Perplexity setup for current rates, quotas, and billing details.
Compatible frameworks and tools
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.
Check the Orq.ai integration documentation for the latest setup options and compatibility information for Perplexity.
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
Anthropic
Access Anthropic’s Claude models through Orq.ai for reasoning, coding, vision, and agentic workflows through one API.
Chat
Reasoning
Vision
Models:
claude-opus-5
claude-sonnet-5
claude-fable-5
Open AI
Access OpenAI models through Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
gpt-5.5 (EU)
gpt-5.6-luna (EU)
gpt-5.6-sol (EU)
Google AI
Access Google’s AI models through Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
gemini-3.5-flash-lite (Gemini API)
gemini-3.6-flash (Gemini API)
Gemini 3 Pro Image
AWS
Access foundation models available through Amazon Bedrock using Orq.ai for reasoning, coding, multimodal, and other AI workloads through one API.
Chat
Reasoning
Vision
Code
Models:
eu.anthropic.claude-opus-5
global.anthropic.claude-opus-5
us.anthropic.claude-opus-5
