Sonar

Sonar by Perplexity: $1 input and $1 output per 1M tokens, 127K context. Call it through the odnoga LLM gateway.

ToolsJSON modeStreaming

Sonar is served by Perplexity and called through odnoga with the same OpenAI-compatible request shape as every other model in the catalog. It supports tool and function calling. It can be forced to return structured JSON. Its 127K-token context window sets how much input you can send in one request.

Specification and price

VendorPerplexity
Model IDsonar
Context window127K tokens
Max output8K tokens
CapabilitiesTools, JSON mode, Streaming
Your plan
Per 1M tokensVendor costYour price on Free+7%
Input$1$1.08
Output$1$1.08
Cached input

Vendor cost is the list price per million tokens as recorded in the odnoga catalog; your price applies your plan margin with the same formula that bills every request — see pricing. Pricing

Call it through odnoga

const res = await fetch("https://api.odnoga.com/v1/chat/completions", {
  method: "POST",
  headers: {
    Authorization: `Bearer ${process.env.ODNOGA_API_KEY}`,
    "Content-Type": "application/json",
  },
  body: JSON.stringify({
    model: "sonar",
    messages: [{ role: "user", content: "Hello" }],
  }),
});

Same request shape for every vendor in the catalog — swap the model id and odnoga handles keys, routing, limits and cost accounting.

How to use Sonar

Derived from the odnoga catalog record for this model.

Best for

  • High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries.
  • Agents and workflows that call your own functions, because the model supports tool calling.
  • Machine-readable output you can write straight into a database, using enforced JSON.
  • User-facing chat where partial output should appear while the model is still writing.

Not the right pick when

  • Anything that needs to read an image — this model takes text only.
  • Very long generated documents — output is capped at 8K tokens per response.
  • Anything where a wrong answer is costly without a human check — no model in the catalog removes that requirement.

Practical tips through odnoga

  1. 01Pin the model id in a managed prompt version, so a model swap is a version change you can compare and roll back, not an edit in application code.
  2. 02Compare it against 2–8 other models on the same frozen test cases in the evaluation laboratory before you make it the production default.
  3. 03For repeated identical deterministic calls, odnoga answer reuse returns the stored answer and bills no vendor tokens — turn it off for creative output.
  4. 04Ask for JSON through the response format rather than in the prompt text — the schema is enforced instead of suggested.
  5. 05Set a fallback model on the route so a vendor incident degrades quality instead of returning an error, and a per-tenant budget so one caller cannot spend the month.

What a month costs

1,000 calls a month, 10,000 input tokens and 2,000 output tokens each, at your Free price (vendor cost +7%):

Input (10M tokens)$10.75
Output (2M tokens)$2.15
Your cost per month on Free$12.90

Vendor list cost $12.00 + odnoga margin $0.903 (+7%). Cached input or answer reuse lowers it; odnoga records both numbers per request.

Sonar compared

ModelContextInput / 1MOutput / 1MCapabilities
Sonar127K$1$1Tools, JSON mode, Streaming
Sonar Pro200K$3$15Tools, JSON mode, Streaming

Questions

How much does Sonar cost per 1M tokens?
Perplexity lists $1 / $1 per 1M input / output tokens in the odnoga catalog. Through odnoga you pay that vendor price plus your plan margin, and every request is recorded with both numbers.
What is Sonar best for?
High-volume, latency-sensitive calls: classification, extraction, routing, short rewrites and summaries. Agents and workflows that call your own functions, because the model supports tool calling. Machine-readable output you can write straight into a database, using enforced JSON.
Can I switch to Sonar without changing my code?
Yes. odnoga exposes one OpenAI-compatible endpoint, so switching means sending "sonar" as the model id — or changing it in the managed prompt version, with no application deploy.
How large is the Sonar context window?
127K tokens of input, with up to 8K tokens of output per response.

All models · Pricing · Docs · Compare models in the evaluation lab

Other Perplexity models

One gateway, every model.