Perplexity API vs DeepInfra
LLM API Providers pricing comparison · 2026
Perplexity API pricing ranges from $1–$15/per million tokens + per-request fee, while DeepInfra ranges from $0.02–$82.5/per million tokens. These products use different pricing models (Per-seat subscription vs Usage-based (pay per token/image/minute)), so a direct price comparison isn't meaningful — costs depend on usage volume and mix.
LLM API Providers
Perplexity API
$1–$15
/per million tokens + per-request fee
Full pricing breakdown →
VS
Perplexity API and DeepInfra both operate in the llm api providers category. This page compares their list pricing.
Plan-by-Plan Pricing
| Plan | Perplexity API | DeepInfra |
|---|---|---|
| Sonar | Custom | Custom |
| Sonar Pro | Custom | — |
| Sonar Reasoning Pro | Custom | — |
| Sonar Deep Research | Custom | — |
Cost at Scale
Total cost of ownership — licenses, implementation, and hidden costs included.
Perplexity API
3 scenarios$2/month ($1 input + $1 output per 1M tokens, via OpenRouter)
Light Usage: Sonar (1M tokens/month)
$18/month ($3 input + $15 output per 1M tokens, via OpenRouter)
Mid-Volume: Sonar Pro (1M tokens/month)
$10/month ($2 input + $8 output per 1M tokens, via OpenRouter)
Reasoning Workload: Sonar Reasoning Pro (1M tokens/month)
DeepInfra
4 scenarios$500
Budget Developer / Experimenter
for ~18.5M queries
~$30/year at 50M output tokens/month
Small SaaS App (8B Model, Moderate Volume)
~$36,000/year at 10B tokens/month
Production SaaS at Scale (Mixed 70B-Class Models)
Contract Terms
| Term | Perplexity API | DeepInfra |
|---|---|---|
| Auto-renewal | No | No |
| Cancellation | N/A — pay-as-you-go, no subscription required | No contract — pay-as-you-go, stop usage anytime |
| Minimum commitment | None | None |
| Price escalation | No published schedule; no mid-cycle price increase reported in sources | No published schedule; per-token prices have generally decreased over time as the inference market has become more competitive |
| Can downgrade | Yes | Yes |