Skip to content
Vercel AI Gateway

Perplexity/Sonar Reasoning Pro

Perplexity/Sonar Reasoning Pro is available via Vercel AI Gateway with a 127K context window and up to 8,000 output tokens. Pricing: $2.00/1M input tokens, $8.00/1M output tokens.

Perplexity/Sonar Reasoning Pro Pricing & Specifications

Input Price$2.00 per 1M tokens
Output Price$8.00 per 1M tokens
Context Window127,000 tokens (127K)
Max Output8,000 tokens
ProviderVercel AI Gateway

What is Perplexity/Sonar Reasoning Pro?

Perplexity/Sonar Reasoning Pro is a large language model by Vercel AI Gateway with a 127K context window and up to 8,000 output tokens. It costs $2.00 per 1M input tokens and $8.00 per 1M output tokens. Perplexity/Sonar Reasoning Pro is available via Vercel AI Gateway with a 127K context window and up to 8,000 output tokens. Pricing: $2.00/1M input tokens, $8.00/1M output tokens.

Capabilities

text

Perplexity/Sonar Reasoning Pro Cost Examples

Short prompt (500 tokens)

$0.001000

Medium prompt (2K tokens)

$0.00400

Long output (4K tokens)

$0.03200

Count tokens for Perplexity/Sonar Reasoning Pro

Paste your prompt to see exact token counts and API cost estimates.

Open Token Counter

Similar Models to Perplexity/Sonar Reasoning Pro

Vercel AI Gateway

Mistral/Magistral Medium

$2.00/1M in 128K ctx

Vercel AI Gateway

Mistral/Mistral Large

$2.00/1M in 32K ctx

Vercel AI Gateway

Mistral/Pixtral Large

$2.00/1M in 128K ctx

Vercel AI Gateway

Openai/Gpt 4.1

$2.00/1M in 1.0M ctx

Frequently Asked Questions

How much does Perplexity/Sonar Reasoning Pro cost per token? +
Perplexity/Sonar Reasoning Pro costs $2.00 per 1M input tokens and $8.00 per 1M output tokens. For a typical 1,000-token request with a 500-token response, that works out to roughly $0.006000.
What is the context window for Perplexity/Sonar Reasoning Pro? +
Perplexity/Sonar Reasoning Pro supports a context window of 127,000 tokens (127K). This determines the maximum combined length of your prompt and conversation history in a single API call.
What is the maximum output length for Perplexity/Sonar Reasoning Pro? +
Perplexity/Sonar Reasoning Pro can generate up to 8,000 tokens in a single response. If you need longer outputs, you can make multiple API calls and concatenate the results.
Is Perplexity/Sonar Reasoning Pro good for coding tasks? +
Perplexity/Sonar Reasoning Pro can handle basic coding tasks, but there are models specifically optimized for code generation that may perform better on complex programming problems.
Token Counter | Pricing Calculator | Model Comparison | All Vercel AI Gateway Models