KymaKyma
Perplexity

Perplexity

Sonar Pro

Sonar Pro is a web-search model built for deep, multi-step research and generating longer, cited reports. Reach for it when you need answers grounded in live web data rather than static training knowledge.

Modalities

Text+Image → Text

Below release

Not established

Weights

Not established

Where it sits in the catalogue Kyma measures

Every number against every text model Kyma prices per token — a stated rule, not a chosen line-up.

Price · input#51/59

$4.05

output $20.25

median $1.009 · best $0.0494

Price · output#51/59

$20.25

per 1M tokens generated

median $3.528 · best $0.2164

Availability · 30d#47/59

96.26%

401 observations since 2026-05-25

median 98.1% · best 100.0%

Throughput#52/59

20.5 tok/s

probe median, one fixed prompt

median 40.0 tok/s · best 314.3 tok/s

Response time#24/59

2.01 s

probe median, to a complete answer

median 2.28 s · best 0.84 s

Context

200K

max output 8,000

published by Perplexity, not measured here

Tick above each rail is this model, below it the other 58. Dashed rule is the field median, solid is its best. Better is left; the axis stops at the 90th percentile, so a few models sit past its right edge.

Usage

How much this model is actually called here.

Rank

#67

of 104 active models

Tokens served

11.5K

all-time

Platform share

0.0%

of all tokens

Pricing

Pay per token. Cached input bills at this model’s own cached rate, listed below.

$4.05 /1M input$20.25 /1M output
Hobby10 req/day · 2K in / 500 out
~$5.47/mo
Production1,000 req/day · 2K in / 500 out
~$547/mo
Scale20,000 req/day · 2K in / 500 out
~$10,935/mo
+ Estimate your workload
1,000
2,000
500

Estimated monthly cost

$547

$18.23 / day on Sonar Pro

Same workload on:

Sonar$101-81%
Claude Fable 5$1,823+233%

Estimates use list pricing. Actual bills depend on real token counts, and every response includes its exact cost.

When to use Sonar Pro

Updated 2026-07-31

Where this model earns its cost — and where it doesn't.

Sonar Pro integrates live search directly into its generation pipeline. It performs multi-step queries to retrieve current information and returns detailed answers with explicit citations. The model accepts text and image inputs and outputs text only.

On Kyma, it runs with a 200,000-token context window and an 8,000-token maximum output. It does not support function calling, structured outputs, or reasoning traces, and it operates at a medium speed tier. It is classified as a premium tier model, and each request incurs a per-request search fee on top of standard token costs.

Kyma handles routing with automatic failover and includes exact request costs in the usage.cost field. Prompt caching is supported, and cached input prefixes are billed at this model's cached input rate. The X-Kyma-Model header confirms the active model for every response.

Deep web research

Query complex topics and retrieve synthesized answers grounded in live sources.

Current events analysis

Track recent developments and generate summaries based on up-to-date reporting.

Long-form cited reports

Draft detailed documents with inline citations and multi-step information gathering.

Image-assisted research

Analyze uploaded images alongside live web queries to contextualize visual data.

Not ideal for: Do not use this model for low-latency conversational chat, function calling, or tasks requiring strict JSON formatting.

How it compares

Against the peers people actually weigh it against.

SpecSonar ProSonarClaude Fable 5
Input /1M$4.05$1.35$13.50
Output /1M$20.25$1.35$67.50
Context200K127K1M
ToolsNoNoYes
ReasoningNoNoYes
Throughput20.5 tok/s21.3 tok/s14.7 tok/s

Quick start

Up and running in under two minutes.

  1. 1

    Create an API key

    Sign up and grab a key from the dashboard — $0.50 free credit, no card required.

    Get API key →
  2. 2

    Make your first request

    Drop in your key and send a chat completion — fully OpenAI-compatible.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro",
    "messages": [
      {"role": "user", "content": "Explain prompt caching in one paragraph."}
    ]
  }'
  3. 3

    Stream responses

    Add "stream": true to receive tokens as they arrive.

    curl https://kymaapi.com/v1/chat/completions \
  -H "Authorization: Bearer YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "sonar-pro",
    "stream": true,
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

FAQ

Common questions about this model.

What is the context window of Sonar Pro?

Sonar Pro has a 200K-token context window — roughly 294 pages of text in a single request.

How much does the Sonar Pro API cost?

$4.05 per 1M input tokens and $20.25 per 1M output tokens. No subscription; you pay only for what you use.

Does Sonar Pro support function calling?

No — Sonar Pro does not support tool calling. For agent workloads, choose a tools-enabled model from the catalog.

Are the weights for Sonar Pro publicly available?

Kyma cannot say. We could not establish it from Perplexity's own material — neither a published checkpoint under Perplexity's own account, nor a statement from Perplexity that the weights are withheld. So we publish "not established" and make no claim in either direction. Treat that as Kyma declining to guess, not as evidence about Perplexity: the honest answer to a question nobody sourced is that nobody sourced it.

Is Sonar Pro ever served below the precision its creator released it at?

Kyma cannot say, and the reason runs one step deeper: we could not even establish whether Perplexity publishes Sonar Pro's weights, so there may be no released checkpoint to compare a route against at all. We publish "not established" rather than reading a low format as a downgrade: on several models in this catalogue a low format is exactly how the creator ships it.

How do I use Sonar Pro?

Kyma is OpenAI-compatible: point your SDK's base URL at https://kymaapi.com/v1, use your Kyma API key, and set the model to sonar-pro. Signing up is free and includes $0.50 of credit — no card required.

Does Sonar Pro support function calling or structured outputs?

No. The model does not support tools or structured output modes; it is optimized for text generation with web citations.

How is search pricing handled on Kyma?

Each request incurs a per-request search fee in addition to standard token costs, billed separately from the input and output rates.

Can I cache prompts to reduce costs?

Yes. Prompt caching is supported, and Kyma bills cached input prefixes at this model's cached input rate.

Start with $0.50 free credit — no card required.Create account →

More models by Perplexity

ModelContextInputOutput
PerplexitySonar127K$1.35$1.35