rapide, recherche-augmented modèle de fondation développé pour instant web citations, up-à-le-minute facts, et concise factual résumés.
Technical Specifications
- Provider
- Perplexity
- Category
- lightweight
- Release Date
- 2024-01
- Batch API Discount
- Standard rate
- Consumer Subscription
- $20 / month
- Reasoning Effort Control
- Fixed
- Structured Outputs
- Yes
- Output Modalities
- text
- Official Documentation
- Visit Official Docs ↗
Data Privacy, Licensing & Deployment Governance
Official Provider Release Intelligence, API Quotas & Agentic Specs
- Official API Model ID (SDK String)
- sonar
- Supported SDK & API Protocol
- Perplexity REST API (OpenAI-Compatible)
- Lifecycle & Deprecation Status
- Legacy Stable (Upgrade path available in Perplexity lineup)
- Production Rate Limits (RPM & TPM)
- 5,000 – 15,000 RPM (Production Tier) · 800,000 – 2,000,000 TPM
- Long-Context Pricing Tier (>128K / >200K)
- Flat rate ($1/1M in) across full 128K window
- Prompt Cache Write & TTL Policy
- Cached input at $0.1/1M tokens
- Computer Use & Browser GUI Agent
- API / CLI Tool-Use & DOM Agent ready (no raw pixel desktop click loop)
- MCP & Parallel Tool Calling
- Native MCP Client/Server ready · Parallel function calling · 100% Strict JSON Schema
- Web Search Grounding & Code Sandbox
- Supported via external Tavily/Exa Search & E2B/Docker Sandbox tools
- Fine-Tuning & Distillation Support
- API Prompt Engineering & RAG Distillation
- Multimodal Tokenization Billing
- Text BPE (~4 chars/token)
- Weights Precision & Quantization
- Cloud-Hosted Proprietary (FP8 / BF16 Tensor Core Cluster)
- Minimum GPU VRAM Requirement
- Zero Local VRAM Required (100% Serverless Cloud API)
- Supported Inference Engines
- Managed Perplexity Cloud API
- System Card & Safety Framework
- Perplexity Production Safety & Alignment Verified
- Enterprise Compliance (SOC2 / HIPAA / ZDR)
- SOC2 Type II · GDPR · Zero Data Retention (ZDR) & HIPAA BAA Available on Enterprise Tier
Sonar Cost, Context, Hardware & API Integration
For single-user chat, a $20/mo subscription caps your bill below this API volume.
Break-even point: ~208 requests/day equals $20/month.
Same Monthly Workload Cost Across Popular Reference Models
Live Prompt Paste Tokenizer & Cost Counter
Paste real system instructions, JSON schemas, or code to measure BPE token counts across tokenizers.
Hybrid Prompt Routing Cascade Simulator
Route routine queries to a fast lightweight model ($0.15/1M) and escalate only complex reasoning turns to Sonar:
Benchmark Scores & 6-Axis Capability Radar
- MMLU-Pro
- 71%
- HumanEval
- 74%
- Chatbot Arena Elo
- 1245pts
Strengths
- Zero-day en temps réel factual précision via automatisé en direct web index scraping
- Exact URL source citations embedded directly dans generated prose
- Clean factual ancrage minimizing hallucinations sur breaking news
Limitations & Trade-offs
- manque d'advanced standalone code architecture ou theoretical STEM proofs
- fenêtre de contexte limité à 128K tokens avec un 4K max sortie cap
Editorial Assessment
le gold standard pour rapide, source-cited conversationnel web recherche.
Best for: Current news synthèse, en direct market recherche, et factual recherche moteur replacement
Compare Sonar
Frequently Asked Questions about Sonar
How much does the Sonar API cost per 1M tokens?+
Sonar by Perplexity is priced at $1 per 1M input tokens and $1 per 1M output tokens. With prompt caching enabled, cached input tokens cost $0.1 per 1M tokens, and asynchronous Batch API requests receive a 0% discount.
Should I use a $20/month subscription or the Sonar pay-as-you-go API?+
A flat $20/month consumer subscription is predictable for daily interactive chat and manual coding. However, if you are building software, running automated workflows, or sending low-to-moderate volume with prompt caching enabled, the pay-as-you-go API is typically far more cost-effective and offers higher rate limits without manual UI caps.
How many words and pages fit in Sonar's context window?+
Sonar features a 128K tokens context window, which equals approximately 96,000 English words or ~256 standard single-spaced pages in a single prompt. Its maximum output generation per turn is 4,096 tokens.
Can I run Sonar locally on my own GPU (Open Weights)?+
No, Sonar is a proprietary closed-weights model hosted by Perplexity. It cannot be downloaded for local GPU execution and must be accessed via Perplexity's official API or cloud platform.
Does Perplexity train on data sent to the Sonar API, and is commercial use allowed?+
API payloads are excluded from model training by default. License tier: Proprietary Commercial API (Perplexity Terms). Full commercial ownership of generated outputs. Supported deployment channels include: Perplexity Cloud API & Enterprise Endpoints.
How does Sonar perform on coding and reasoning benchmarks?+
Sonar achieves a composite Intelligence Index of 73/100, scoring N/A% on SWE-bench Verified, N/A% on GPQA Diamond, 71% on MMLU-Pro, and 1245 pts on Chatbot Arena Elo.
What is Sonar best used for?+
Sonar is best suited for: Current news synthèse, en direct market recherche, et factual recherche moteur replacement. Assessment: le gold standard pour rapide, source-cited conversationnel web recherche.
Perplexity Family Lineage, Routing Tiers & Upgrade Path
Step down to a lighter sibling for high-volume routing or step up to Perplexity's flagship reasoning tier:
AI Glossary & Architecture Concepts
View full glossary →Key machine learning concepts and benchmarks relevant to Sonar:
L'unité textuelle de base traitée par un modèle linguistique, représentant généralement 3 à 4 caractères ou environ 0,75 mot. Par exemple, une phrase courante est découpée en plusieurs jetons.
Une suite de tests standardisés permettant d'évaluer et de comparer objectivement les performances des modèles d'IA sur des tâches ciblées (code avec SWE-bench, mathématiques avec AIME, etc.).
Le nombre maximal de jetons qu'un modèle peut traiter simultanément (entrée et sortie comprises). Une fenêtre de 1 000 000 jetons permet d'analyser environ 750 000 mots en une seule requête.
La capacité d'un LLM à déterminer quand une action externe est requise et à générer des arguments structurés pour invoquer des API, calculatrices ou bases de données avant de poursuivre.
Un standard ouvert créé par Anthropic permettant aux agents d'IA de se connecter de façon uniforme aux systèmes de fichiers locaux, aux environnements de développement et aux API tierces.
Une optimisation tarifaire et technique conservant les états d'attention des préfixes de prompts récurrents, réduisant les coûts d'entrée de 50 à 90 % tout en abaissant la latence.
Les scores de benchmarks, tarifs par token et limites évoluent rapidement. Vérifiez toujours les spécifications actuelles sur la documentation officielle du fournisseur.