All Models / Provider

perplexity API Models & Token Pricing (5 Models)

Complete live per-token pricing table for all 5 perplexity models, updated automatically.

ModelContextInput / 1MOutput / 1MCache Read / 1M
Perplexity: Sonar
perplexity/sonar
127K $1.00 $1.00 —
Perplexity: Sonar Deep Research
perplexity/sonar-deep-research
128K $2.00 $8.00 —
Perplexity: Sonar Reasoning Pro
perplexity/sonar-reasoning-pro
128K $2.00 $8.00 —
Perplexity: Sonar Pro
perplexity/sonar-pro
200K $3.00 $15.00 —
Perplexity: Sonar Pro Search
perplexity/sonar-pro-search
200K $3.00 $15.00 —

Recommended AI & GPU Infrastructure

Best for H100 / A100 / 4090

RunPod Cloud GPUs

Spin up on-demand H100, A100, and RTX 4090 pods or serverless vLLM endpoints in seconds.

Launch GPU on RunPod →
Predictable Cloud Infra

DigitalOcean GPU Droplets

Deploy AI inference APIs, vector databases, and GPU droplets with simple monthly billing.

Try DigitalOcean →
Global Low-Latency Regions

Vultr Cloud GPU

Run dedicated NVIDIA H100/A100/L40S instances across 32 global data center regions.

Deploy on Vultr →
1 API Key · 470+ Models

OpenRouter Unified API

Switch between Gemini, Claude, GPT, DeepSeek, and Llama with one OpenAI-compatible key.

Get Unified API Key →