Vigia

AI model · Perplexity

Perplexity: Sonar available

perplexity/sonar

Perplexity: Sonar costs US$ 1.00 per million input tokens and US$ 1.00 per million output tokens (OpenRouter reference price, verified 2026-11-12).

Input price (per 1M tokens)US$ 1.00
Output price (per 1M tokens)US$ 1.00
Typical request (2,000 tokens in, 500 out)US$ 0.0025
Context window127,072
Max output tokens114,364
Announced retirement datenone
Knowledge cutoff—
Last verified2026-11-12 17:41:16 UTC

Reference prices from OpenRouter (aggregator); they may differ from the provider's direct pricing.

Frequently asked questions

How much does Perplexity: Sonar cost?

Perplexity: Sonar costs US$ 1.00 per million input tokens and US$ 1.00 per million output tokens (OpenRouter reference price, verified 2026-11-12).

What is the context window of Perplexity: Sonar?

Perplexity: Sonar accepts up to 127,072 tokens of context.

Is Perplexity: Sonar being retired?

No retirement date has been announced for Perplexity: Sonar (checked 2026-11-12).

Other Perplexity models

ModelInput / 1MOutput / 1MContext
perplexity/sonar-pro-searchUS$ 3.00US$ 15.00200,000
perplexity/sonar-reasoning-proUS$ 2.00US$ 8.00128,000
perplexity/sonar-proUS$ 3.00US$ 15.00200,000
perplexity/sonar-deep-researchUS$ 2.00US$ 8.00128,000

Give your AI agent these facts

Vigia is a free MCP server: your coding agent checks versions, breaking changes and vulnerabilities before it writes code. No signup, no API key.

claude mcp add --transport http vigia https://vigia.coredls.cloud/mcp

Add to CursorAdd to VS Code★ Star on GitHub

Any other MCP client
{ "mcpServers": { "vigia": { "url": "https://vigia.coredls.cloud/mcp" } } }

Agent skill (SKILL.md): tells the agent when to use Vigia · GitHub Action for pull requests

For agents

GET https://vigia.coredls.cloud/v1/models/perplexity/sonar