BroadRouter

Sonar API pricing

Updated

The cheapest standard price for Sonar is Perplexity at USD 0.25 per 1M input tokens and USD 2.50 per 1M output tokens. That is Perplexity's own API. Every price is read from the provider's own pricing page, checked 2026-11-15.

Perplexity · slug sonar · 1 provider with a standard price. Every price is read from the provider's own pricing page and linked in its row, checked 2026-11-15. No aggregator feed. Download all prices (every provider and model, with sources, CSV or JSON). How it compares with the market: the LLM API price index.

What does Perplexity charge for Sonar?

Input
USD 0.25
Cached input
USD 0.0625
Output
USD 2.50
Blended 3:1
USD 0.8125

USD per 1M tokens on Perplexity, model perplexity/sonar, standard tier. Source, checked 2026-11-15.

Is a host cheaper than Perplexity? Only Perplexity publishes a standard price for Sonar: USD 0.25 input and USD 2.50 output per 1M tokens. No third-party host lists it on its own pricing page yet.

Sonar price per provider

USD per 1M tokens. Standard prices are ranked on a blend of 3 input tokens to 1 output token, cheapest first.

Sonar API prices by provider
#ProviderInputCached inputOutputBlended 3:1ContextPrecisionSource
1Perplexity cheapest maker
perplexity/sonar
Notes and source quote

Agent API token rates; tool calls (web_search USD 0.0025 per invocation etc.) are billed separately per the pricing page.

“`perplexity/sonar` | 0.25 | 2.50 | 0.0625”
USD 0.25USD 0.0625USD 2.50USD 0.8125not statednot statedPerplexity page
checked 2026-11-15
re-checked 2026-11-16

Report a wrong price or number (email to info@broadnet.ai, with this page's link filled in).

What does Sonar cost for a real workload?

Monthly cost over 30 days at each standard price, using the presets of the LLM API cost calculator. Providers without a cached price bill cached input at the input price.

  • Support chatbot: 2,000 requests a day, 1,500 input tokens (60% cached), 300 output.
  • RAG over documents: 1,000 requests a day, 8,000 input tokens (30% cached), 500 output.
  • Coding agent (one developer): 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning.
Monthly cost of three workloads on Sonar, by provider
ProviderSupport chatbotRAG over documentsCoding agent (one developer)
Perplexity (maker)USD 57.37USD 84.00USD 388.13

Estimate your own bill

Priced closest from other makers: Mistral Medium 3 (Mistral AI, USD 0.80) · Gemini 2.5 Flash (Google, USD 0.85) · Gemini 3.5 Flash-Lite (Google, USD 0.85).

All 428 models: API prices compared · Cheapest LLM APIs right now · LLM API price index (open data) · Download all prices (CSV, JSON) · Price change log

Questions

How much does the Sonar API cost per token?

From USD 0.25 per 1M input tokens (USD 0.00000025 per token) and USD 2.50 per 1M output tokens (USD 0.0000025 per token) at the cheapest standard price. Each price was read from the provider's own pricing page; the source is linked in its row.

Which provider is cheapest for Sonar?

Perplexity is the only provider with a paid standard price, USD 0.25 input and USD 2.50 output per 1M tokens, so there is nothing to rank yet.

Is Sonar cheaper from a host than from Perplexity?

Only Perplexity publishes a standard price for Sonar: USD 0.25 input and USD 2.50 output per 1M tokens. No third-party host lists it on its own pricing page yet.

Does Sonar have cached input pricing?

Yes. The lowest is USD 0.0625 per 1M at Perplexity. Providers without one bill cached input at the input price. What cached input means.

How much does a coding agent cost per month on Sonar?

For 1,500 requests a day, 40,000 input tokens (85% cached), 2,000 output incl. reasoning, over 30 days: USD 388.13 a month at Perplexity. Most of the input is cached, so the cache price matters as much as the input price. Try your own numbers.

Is Sonar free to use through an API?

No provider in our data lists a free price for Sonar as of 2026-11-15. Free tiers and credits by provider (checked 2026-11-14) lists general offers that do not name a model.

Read as MarkdownAsk ChatGPTAsk ClaudeAsk Perplexity