Skip to content
Model infoModelsSnapshot: 15 Oct 2026

Perplexity / Sonar

Sonar

Perplexity’s native language model for grounded search, selectable through the Agent API.

Language models (LLMs)
availableClosed weightsText generationSearch
Official documentation (opens in a new tab)Reviewed 14 Oct 2026
6 of 18 specification fields collected
Context windowNot collectedAwaiting source review
Maximum outputNot collectedAwaiting source review
Input / 1M tokens$0.25Perplexity Agent API
Output / 1M tokens$2.50USD · observed 12 Oct 2026

Specifications

Provider-documented facts. “Not collected” means we have not verified that field yet, not that the feature is unsupported.

Context / input limit
Not collected
Maximum output
Not collected
Input modalities
TextSource for Input modalities (opens in a new tab)
Output modalities
TextSource for Output modalities (opens in a new tab)
Reasoning
Not collected
Tool calling
Not collected
Structured output
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Batch processing
Not collected
Fine-tuning
Not collected
Knowledge cutoff
Not collected
Release date
Not collected
Parameters
Not collected
Architecture
Not collected
Languages
Not collected
Context caching
SupportedSource for Context caching (opens in a new tab)

A published cache-read rate proves billing support; cache controls and lifetime are not yet verified.

Search grounding
SupportedSource for Search grounding (opens in a new tab)
Version changes
The February 11, 2025 Sonar release was further trained from Llama 3.3 70B for grounded answer factuality and readability.Source for Version changes (opens in a new tab)

This historical lineage is not proof of the exact weights, parameters or limits behind the current Agent API selector.

Access & pricing

Prices belong to an endpoint and billing tier. A provider listing does not guarantee access for every account or region.

Perplexity Agent API · default

Provider source (opens in a new tab)
API model ID
perplexity/sonar
Access
Perplexity API key; POST https://api.perplexity.ai/v1/agent (compatibility alias: /v1/responses). Set service_tier=default. auto or an omitted tier also selects default processing.
Regions
Not collected
Streaming
SupportedSource for Streaming (opens in a new tab)
Context caching
SupportedSource for Context caching (opens in a new tab)
Service tier
defaultSource for Service tier (opens in a new tab)
INPUT / 1M TOKENS$0.25
OUTPUT / 1M TOKENS$2.50

Perplexity Agent API default processing; USD per million tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero. Cached input price: $0.0625 / 1M tokens (base tier).

USD · observed 12 Oct 2026 · Pricing evidence (opens in a new tab)
Published billing units · original currency · observed 12 Oct 2026
CategoryUsageRateUnit
Tool add-onWeb search1$0.0025invocation
Tool add-onFast search2$0.001invocation
Tool add-onImage search3$0.0025successful invocation
Tool add-onURL fetch4$0.0005invocation
Tool add-onPeople search5$0.005invocation
Tool add-onFinance search6$0.005invocation
Tool add-onCode sandbox7$0.03container session
Tool add-onSearch inside sandbox8$0.0025SDK search request

Rate conditions

  1. Standard web search. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  2. web_search with search_type=fast. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  3. Image search bills successful invocations. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  4. Fetch and extract URL content. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  5. People search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  6. Financial search tool. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  7. Up to 20 minutes of active use per billing window; this is not a runtime cap. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
  8. Additional SDK search calls made inside a sandbox. Optional Agent API tool usage is separate from token billing. This fee is not proof that this model supports every tool. Token service-tier multipliers are not applied to these tool fees.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Perplexity Sonar Chat Completions (legacy)

Provider source (opens in a new tab)
API model ID
sonar

Exact provider-listed historical selector.

Access
Legacy support ended September 27, 2026. Synchronous/streaming requests continue through gradual Agent API reformulation. No separate independent model record is created for this compatibility surface.
Regions
Not collected

Prices retain their published currencies and billing units below.

Published billing units · original currency · observed 14 Oct 2026
CategoryUsageRateUnit
Historical Sonar pricingInput tokens1$1.001M tokens
Historical Sonar pricingOutput tokens1$1.001M tokens
Historical Sonar pricingRequest fee: low search context1$5.001K requests
Historical Sonar pricingRequest fee: medium search context1$8.001K requests
Historical Sonar pricingRequest fee: high search context1$12.001K requests

Rate conditions

  1. Historical Sonar calculator rates retained in official documentation captured October 14, 2026. Legacy support ended September 27, 2026; current synchronous/streaming requests are translated to Agent API. Effective dates and ongoing applicability of these legacy rates are unverified. These are not current Agent API prices or a complete cost-per-question quote. Pro Search rates are explicitly excluded from the calculator. No cache rate is supplied for these legacy tiers.
Pricing source (opens in a new tab)

Data & enterprise terms

Retention, training use, regional processing and enterprise terms have not been summarized for this endpoint.

Caching

Caching can reuse earlier input processing. Availability, lifetime and billing depend on the endpoint. A cache hit still generates a new response.

01 / INITIAL INPUTProcess & retain

The system processes eligible input and retains reusable state.

02 / LATER REQUESTCheck available state

Reuse depends on matching input, session state and the cache policy.

03 / CACHE HITReuse & generate

Reusing state can reduce repeated work. Any charges follow the billing rules below.

Perplexity Agent API · default

perplexity/sonar
Documented
Support evidence (opens in a new tab)
How it works
Not collected
Minimum reusable input
Not collected
Lifetime & refresh
Not collected

Do not inherit the model developer’s direct-API retention policy onto the Perplexity endpoint.

How to enable it
Not collected
Usage fields
The Agent API response usage object reports input, output and cache-read token counts. Compare these metered counts with the applicable endpoint rate.Source for Usage fields (opens in a new tab)

This reporting contract does not establish cache eligibility, prefix minimum, cache-write controls or retention lifetime.

Billing rules
Published discounted cache-read rates apply to this default service tier. Write charges, minimum cacheable input, retention and cache controls have not been verified for this host.Source for Billing rules (opens in a new tab)
Limits & data boundaries
Not collected
Cache reads, writes & storage
ChargeApplies toRate / unit
Cache read1Text tokens · Base tier$0.0625 / 1M tokensPricing evidence (opens in a new tab)

Rate conditions

  1. Perplexity Agent API default processing; USD per million tokens. Tool calls are charged separately when used. Rates are host-specific, not the model developer’s direct-API prices. Unknown cache-write charges are not treated as zero.

Observed 12 Oct 2026. Write rates and storage fees are different charges; use the billing rules above.

Caching reviewed 14 Oct 2026

Perplexity Sonar Chat Completions (legacy)

sonar
Not verified

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

How it works
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

Minimum reusable input
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

Lifetime & refresh
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

How to enable it
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

Usage fields
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

Billing rules
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

Limits & data boundaries
Not collected

Historical exact-model cache contract not verified. Current Agent API cache rates are not inherited.

No verified cache rate for this endpoint. An empty rate is not a zero charge.

Caching reviewed 14 Oct 2026

What the measurements say

No benchmark observations have been added for this model. We do not turn a vendor description into a performance score.

Latency and throughput depend on the host, request size, reasoning settings and load. There is no measured speed or global usage figure in this record.

The record behind the model

Why it is included

Inference from the current catalog identifying Sonar as Perplexity’s own model, the official help center calling it an in-house model, and the reviewed official public-weight inventory having no Sonar release. This is not an explicit weight-license declaration. Search presets and third-party open-weight models are not classified as native closed models.

Classification evidence (opens in a new tab)

Lifecycle dates

Legacy Chat Completions support ended; Agent API model remains listed27 Sept 2026Source (opens in a new tab)

Sources reviewed