LIVE
Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|Google Introduces "Gemini 4 Carbon" as Next Step in Its Model Lineup28/10/26 · Google|DeepMind unveils Genie 4, a new generation of world model27/10/26 · Google DeepMind|Anthropic files IPO prospectus, with risk disclosures taking center stage26/10/26 · Anthropic|Robot policy trained only in simulation matches top real-world systems26/10/26|OpenAI unveils GPT-6.1 Terra, a model built for computer use26/10/26 · OpenAI|Google's AI gives evasive answers about who won the 2020 US election28/10/26 · Google|NVIDIA introduces Nemotron 3.5 Transcribe, a promptable multilingual transcription model28/10/26 · NVIDIA|OpenAI and ServiceNow deepen partnership on enterprise workflows28/10/26 · OpenAI|Failed startups' data finds a second life training AI models28/10/26|Anthropic expands AI for Science program to 20 foundations and research institutions28/10/26 · Anthropic|Anthropic shares early results on using Claude to accelerate drug development27/10/26 · Anthropic|GEPA-Curator: Filtering Failures to Better Train LLM Agents27/10/26|
Toolofficial publisher

Perplexity Sonar API

Tool : A precise action the AI can call · requires perplexity-api

Cited, ready-to-use answers for an agent.

Web search with a written answer in one call.

Docs
Overall score
6.4 /10
Security: one caveat, see the card
Utility
7.0
Reliability
6.0
Security
One caveat
Ease
5 min · Comfortable

Security reflects where data goes, requested permissions and incidents on record at the verification date. It is not a guarantee of zero risk: check the deployment mode and the connections you enable.

What it does, concretely

Getting reliable, sourced answers from the web in a single API call is often complex: you need to query a search engine, retrieve pages, parse them, and then write a summary. Perplexity Sonar API consolidates these steps into one request.

Concretely, the API exposes several endpoints: an Agent API that returns written answers with built-in citations, a Search API that provides raw ranked web results with advanced filtering and real-time data, and access to third-party models (OpenAI, Anthropic, Google, xAI) augmented with web search tools and presets. Everything is OpenAI-compatible, making integration into existing pipelines straightforward.

This service targets developers and technical teams building agents, assistants, or applications that require recent and verifiable web data, without having to assemble a search pipeline themselves.

It is not suited for non-technical users looking for a consumer-facing interface, nor for projects with a fixed budget, since billing is usage-based according to the number of requests and tokens consumed.

What it offers

  • ·Agent API: returns a written answer with built-in web citations in a single call. (paid)
  • ·Search API: provides raw, ranked, and filterable web results in real time. (paid)
  • ·Router API: unified access to open-weight models hosted by Perplexity through one OpenAI-compatible endpoint. (paid)
  • ·Access to third-party models (OpenAI, Anthropic, Google, xAI) augmented with web search tools and presets. (paid)
  • ·Embeddings API: generates high-quality embeddings for semantic search and RAG pipelines. (paid)
  • ·OpenAI-compatible format to ease integration into existing architectures. (paid)

In practice

Price
Paid · from 5 €
Commercial use
Commercial use: yes
Available on
api
Host
perplexity-api
FR interface
No

Security and data

Rating
Security: one caveat, see the card
Capabilities
readswritesexecutesnetwork
Your data
Data with the vendor
Maintenance
Active

Links and repository checked on 25 October 2026 · added on 1 January 2025

How to install Perplexity Sonar API

1. Create an account on perplexity.ai and navigate to the API section of your developer dashboard. 2. Generate an API key from the dashboard and store it securely, never hardcoding it in your source code. 3. Consult the /llms.txt file on docs.perplexity.ai to identify relevant endpoints and documentation pages. 4. Make a first test call to your chosen endpoint (Agent API, Search API, or Router API) using the OpenAI-compatible format. 5. Check the responses and citations returned, then adjust parameters or presets to fit your application's needs. 6. Set up consumption monitoring (requests and tokens) to keep costs under control from the development phase onward.
model="sonar"

Official documentation ↗

In the same category

Whole category Feed (memory, context) →