AI Model Watch
Models / Perplexity

Sonar Pro

Deprecated

Advanced search model for complex queries and follow-ups; ~2x more search results than Sonar; non-reasoning. 200K context. Token pricing $3/$15 per 1M in/out. Additional per-request search fee NOT in token price: $6/$10/$14 per 1,000 requests for low/medium/high search context size (pricing page). Supports image input and the Dec 2025 media classifier (auto image/video selection). Max output tokens not published. Knowledge cutoff not published (search-grounded). Pricing page fetched 2026-06-28; token and request rates re-read unchanged on the pricing page 2026-09-29, which still publishes the Sonar API tables. LIFECYCLE (read 2026-09-29): Perplexity's Sonar migration guide states 'Sonar Chat Completions support ended on September 27, 2026. Synchronous and streaming requests keep working: they are being reformulated as Agent API requests, rolling out gradually by model. Asynchronous Sonar requests are not reformulated and are no longer supported'. The changelog files the migration under 'Deprecation' (July 2026, no day given), so deprecated_on carries the stated support-end date, 2026-09-27. Signal used: that first-party sentence. Status is deprecated, NOT retired: Perplexity says synchronous calls still work and states no shutdown date, so retires_on stays null. Perplexity's comparable Agent API preset for Sonar Pro is 'fast' (migration guide mapping table); presets are not catalog models, so replacement stays null. The former per-model docs page now redirects to the migration guide.

Sonar Pro by Perplexity costs $3 per 1M input tokens and $15 per 1M output tokens ($6/1M blended), with a 200K (200.000-token) context window. It is deprecated.

Last verified: 24 Oct 2026 · sourced from official provider documentation

Deprecated since 27 Sep 2026 · no retirement date published

Lifecycle warning

This model is deprecated.

Read the Sonar Pro migration guide → replacement & cheapest alternatives

Provider
Perplexity
Status
Deprecated
Input price
$3 / 1M tokens
Output price
$15 / 1M tokens
Cached input
—
Blended price
$6 / 1M tokens
Context window
200.000 tokens (200K)
Max output
—
Modality
text, image
Open weights
No — API only
Knowledge cutoff
—
Released
Jan 2025
API string
sonar-pro

Source: Perplexity official documentation ↗

See also

Explore more

All Perplexity models→

Prices, context windows and lifecycle status for every Perplexity model we track.

Compare models head-to-head→

Side-by-side price, context and status for the models developers weigh against each other.

FAQ

Sonar Pro — questions & answers

How much does Sonar Pro cost?

Sonar Pro is priced at $3 per 1M input tokens and $15 per 1M output tokens ($6/1M blended at a 3:1 input-to-output ratio).

What is the context window of Sonar Pro?

Sonar Pro has a 200.000-token context window (200K).

Is Sonar Pro being deprecated or retired?

Sonar Pro is deprecated. It was deprecated on 27 Sep 2026; no retirement date has been published yet.

Does Sonar Pro support image or vision input?

Yes — Sonar Pro accepts image input. Listed modalities: text, image.

Can I self-host Sonar Pro?

No — Sonar Pro is proprietary. Its weights are not publicly released, so it is available only through Perplexity's API (or hosted partners), not for self-hosting.

What is the API model string for Sonar Pro?

The API model identifier for Sonar Pro is "sonar-pro" when calling Perplexity's API.