Sonar Reasoning Pro
Sonar Reasoning Pro combines the deepest web retrieval in the Sonar family with chain-of-thought reasoning to return well-sourced, structured answers within a context window of 127K tokens.
View API reference- Input and output price
- Input $2, Output $8, Per 1M tokens
- 24h uptime
- Loading AI Gateway uptime
import { streamText } from 'ai'
const result = streamText({ model: 'perplexity/sonar-reasoning-pro', prompt: 'Why is the sky blue?'})Copy link to headingPlayground
Try out Sonar Reasoning Pro by Perplexity. Usage is billed to your team at API rates. Free users (those who haven't made a payment) get $5 of credits every 30 days.
Sonar Reasoning Pro
Sonar Reasoning Pro
Copy link to headingProviders
Route requests across multiple providers. Copy a provider slug to set your preference. Visit the docs for more info. Using a provider means you agree to their terms, listed under Legal.
Copy link to headingUptime24 hours
Direct request success rate on AI Gateway and per-provider. Visit the docs for more info.
Copy link to headingThroughput24 hours
P50 throughput on live AI Gateway traffic, in tokens per second (TPS). Visit the docs for more info.
Copy link to headingLatency24 hours
P50 time to first token (TTFT) on live AI Gateway traffic, in milliseconds. View the docs for more info.
Getting started
Call Sonar Reasoning Pro through AI Gateway with the AI SDK generateText and streamText functions, or through the OpenAI Chat Completions, OpenAI Responses, and Anthropic Messages APIs by changing the base URL. AI Gateway authenticates the request and routes it to an available provider.
Install the AI SDK (pnpm add ai dotenv), create an API key from the API Keys page, and set it as AI_GATEWAY_API_KEY in your environment. Full setup is covered in the text generation quickstart.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'perplexity/sonar-reasoning-pro', prompt: 'Why is the sky blue?', });
console.log(result.text);}
main().catch(console.error);Top-level parameters
The same Sonar Reasoning Pro request in each API format AI Gateway supports.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'perplexity/sonar-reasoning-pro', system: 'You are a concise technical assistant.', prompt: 'Summarize the tradeoffs between static generation and SSR.', maxOutputTokens: 1024, });
console.log(result.text);}
main().catch(console.error);Standard parameters like prompt, messages, temperature, and tools work as documented in the AI SDK docs. These are the parameters with model-specific behavior.
| Parameter | Type | Required | Description |
|---|---|---|---|
model | string | Yes | Model ID in the form creator/model, e.g. perplexity/sonar-reasoning-pro. AI Gateway routes the request to an available provider. |
maxOutputTokens | number | No | Hard cap on generated tokens. Sonar Reasoning Pro supports up to 8,000 output tokens. Reasoning tokens count toward this limit. |
reasoning | 'provider-default' | 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | No | Provider-agnostic reasoning effort, available in AI SDK 7 or later. Maps to the provider’s native reasoning configuration; reasoning settings under providerOptions take precedence when both are set. See the Reasoning section below. |
providerOptions | Record<string, JSONValue> | No | AI Gateway routing options under gateway, plus any provider-native options under the provider’s own namespace — see the table below. |
Input limits
| Input | Formats | Sources | Max count | Max size | Limits |
|---|---|---|---|---|---|
| Text | — | — | — | — | Prompt and response share the 127K-token context window |
| Image | — | URL, base64, Uint8Array | — | — | Sent as image parts in messages; counts as input tokens |
Provider options
Set AI Gateway routing options under providerOptions.gateway. For provider-specific options, pass them under the provider’s namespace as documented by the AI SDK.
Learn more in the AI SDK perplexity provider docs.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'perplexity/sonar-reasoning-pro', prompt: 'Why is the sky blue?', providerOptions: { gateway: { only: ['perplexity'], }, }, });
console.log(result.text);}
main().catch(console.error);These AI Gateway routing options apply to every model. Provider-specific options pass through under the provider’s own namespace (for example providerOptions.anthropic) exactly as documented by the AI SDK.
| Parameter | Type | Required | Description |
|---|---|---|---|
providerOptions.gateway.only | string[] | No | Restrict routing to these provider slugs. Requests fail over only within the listed providers. |
providerOptions.gateway.order | string[] | No | Preferred provider order. Listed providers are tried first; unlisted providers remain available as fallbacks. |
providerOptions.gateway.sort | 'cost' | 'ttft' | 'tps' | No | Rank candidate providers by price, time to first token, or tokens per second instead of the default routing order. |
providerOptions.gateway.zeroDataRetention | boolean | No | Route only to providers with a zero-data-retention policy for this model. |
Routing across providers
AI Gateway serves the same model through multiple providers and fails over automatically. order expresses a preference while keeping every provider eligible; only is a hard allowlist — if none of the listed providers are available the request fails instead of falling back.
Options under a provider's own namespace (for example providerOptions.anthropic) are forwarded to that provider with the request. Providers ignore option namespaces that don't apply to them, so it is safe to set provider options alongside gateway routing options.
Reasoning
AI Gateway bridges reasoning across every API format. The AI SDK exposes a provider-agnostic top-level reasoning level (none, minimal, low, medium, high, or xhigh); the Chat Completions and Responses formats take the same effort under reasoning.effort; and the Anthropic Messages format uses a native thinking token budget. Whichever you send, the gateway maps it to the target model’s native configuration, converting between effort levels and token budgets as needed. Reasoning-related settings under providerOptions take full precedence over the top-level reasoning value and are never merged. Reasoning tokens typically count toward your output-token usage, though how they’re reported and billed varies by provider.
Learn more in the AI Gateway reasoning guide.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'perplexity/sonar-reasoning-pro', prompt: 'Explain the Monty Hall problem step by step.', reasoning: 'high', });
console.log(result.text);}
main().catch(console.error);Image input
Send images alongside text as message parts. Images count as input tokens.
import { generateText } from 'ai';import 'dotenv/config';
async function main() { const result = await generateText({ model: 'perplexity/sonar-reasoning-pro', messages: [ { role: 'user', content: [ { type: 'text', text: 'Describe this image.' }, { type: 'image', image: 'https://example.com/photo.jpg' }, ], }, ], });
console.log(result.text);}
main().catch(console.error);Copy link to headingMore models by Perplexity
| Model |
|---|
| 32K | $0.004/M | — | | 02/26/2026 | ||||||||||
| 32K | $0.03/M | — | | 02/26/2026 | ||||||||||
| 127K | 2.5 s | 82 tps | $1/M | $1/M | $5/K+2 more | | 02/19/2025 | |||||||
| 200K | 1.9 s | 103 tps | $3/M | $15/M | $6/K+2 more | | 02/19/2025 |
Copy link to headingAbout Sonar Reasoning Pro
Sonar Reasoning Pro is the full search-augmented reasoning stack from Perplexity. It combines the deep, multi-source web retrieval of Sonar Pro with chain-of-thought reasoning, producing answers that are both broadly sourced and logically structured.
Perplexity describes benchmark results and search modes for this model in its announcement. See https://sonar.perplexity.ai for methodology, pricing context, and product details.
The practical impact shows up on hard research questions. Queries that require reconciling conflicting sources, reasoning about implications of recent developments, or building a structured argument from scattered web evidence use both retrieval breadth and reasoning depth. The model searches more sources than Sonar Reasoning, applies more deliberation, and returns longer, more structured responses. The context window of 127K tokens supports extended research sessions where accumulated context from prior turns informs later searches and reasoning.
Copy link to headingWhat To Consider When Choosing a Provider
- Configuration: Sonar Reasoning Pro has the highest per-token cost and longest response times in the Sonar family. Use AI Gateway's cost tracking and latency monitoring to profile requests. Confirm the quality gain matches your budget. Web search calls bill separately (N/A per thousand when listed for this model).
- Zero Data Retention: Zero Data Retention is offered on a per-provider and model basis. See the documentation for details.
- Authentication: AI Gateway authenticates requests using an API key or OIDC token. You do not need to manage provider credentials directly.
Copy link to headingWhen to Use Sonar Reasoning Pro
Best for
- Deep research and analysis: Requires both broad source retrieval and multi-step logical reasoning over the evidence
- Strategic decision support: Analysis quality depends on both the breadth of sources consulted and the rigor of reasoning applied
- Complex competitive intelligence: Needs to reconcile conflicting information from multiple sources into one assessment
- Policy and regulatory analysis: Requires structured reasoning across evolving standards, guidelines, and jurisdictional differences
- High-stakes factual analysis: Thoroughness of both retrieval and reasoning affects decision quality
Consider alternatives when
- Straightforward queries: Base Sonar or Sonar Pro answer faster at lower cost without deep reasoning
- Hard latency constraints: Combined deep search and reasoning produces the longest response times in the Sonar family
- Tight per-request budget: Broad retrieval and extended reasoning generate the most output tokens
- Closed-domain problems: A standalone reasoning model fits better when no web grounding is needed
Copy link to headingConclusion
Sonar Reasoning Pro fits when both the breadth of evidence and the depth of reasoning drive answer quality. It brings Perplexity's search and reasoning capability into one API call. It's the Sonar option with the most combined retrieval and reasoning depth for research, analysis, and decision support.
Copy link to headingFrequently Asked Questions
What makes Sonar Reasoning Pro different from Sonar Reasoning?
Sonar Reasoning Pro combines Pro-level deep web retrieval (more sources) with chain-of-thought reasoning. Standard Sonar Reasoning uses base-level retrieval with reasoning. The Pro variant goes further on both search and deliberation.
How does Sonar Reasoning Pro compare to chaining a search API with a separate reasoning model?
Sonar Reasoning Pro integrates search, retrieval, source evaluation, reasoning, and cited answer generation into a single API call. This cuts latency and operational complexity versus wiring separate services. The model is tuned to reason over its own search results.
What types of queries benefit most from Sonar Reasoning Pro?
Competitive intelligence, regulatory research, technical due diligence, and strategic analysis when the answer depends on reasoning across many sources. It fits questions that need both broad retrieval and structured analysis.
What is the context window for Sonar Reasoning Pro?
127K tokens. This supports extended multi-turn research sessions where prior search results and reasoning inform subsequent queries.
How much does Sonar Reasoning Pro cost?
Pricing appears on this page and updates as providers adjust their rates. AI Gateway routes traffic through the configured provider.
How do I authenticate with Sonar Reasoning Pro through AI Gateway?
Use your AI Gateway API key with the model identifier `
perplexity/sonar-reasoning-pro`. AI Gateway handles provider routing and authentication. You don't need a separate Perplexity API key when using gateway-managed access.Does Sonar Reasoning Pro show its reasoning process?
Yes. The chain-of-thought reasoning trace appears in the response. It shows how the model analyzed and connected information from the retrieved sources to reach its conclusion.
Your use is subject to Perplexity's Terms & Privacy Policies.