# Accurate sandbox extraction usage and costs

By Steven Van · 2026-10-01

Successful sandbox extraction calls now count towards Agent API response totals, with pricing unchanged and no historical backfill.

Successful pplx\_sdk.llm.extract calls inside the sandbox tool now have their model token usage and cost included in [Perplexity](<https://creatorstoolbox.com/tools/perplexity>) Agent API responses.

## Where usage and costs appear

Per-model token counts appear in usage.tool\_calls\_details.sandbox.token\_usage. Extraction costs appear in both usage.tool\_calls\_details.sandbox.cost\_usd and usage.cost.tool\_calls\_cost\_details.sandbox, and contribute to usage.cost.total\_cost.

## Existing pricing still applies

The [update](<https://docs.perplexity.ai/docs/agent-api/models>) uses existing openai/gpt-6-luna pricing, including cache creation, cache read, and reasoning-token dimensions. It corrects response-level reporting without changing pricing or backfilling historical responses.

![Perplexity](<https://www.google.com/s2/favicons?domain=perplexity.ai&sz=128>)

Perplexity

AI-powered answer engine — ask anything and get cited, real-time answers from across the web.

[View Perplexity →](<https://creatorstoolbox.com/tools/perplexity>)

Sources

[Original source](<https://docs.perplexity.ai/changelog#october-2026>)

[Read Accurate sandbox extraction usage and costs on Creators Toolbox](<https://creatorstoolbox.com/blog/perplexity-accurate-sandbox-extraction-usage-and-costs>)

---
Canonical source: https://creatorstoolbox.com/blog/perplexity-accurate-sandbox-extraction-usage-and-costs