# Perplexity — Accurate sandbox extraction usage and costs

- Company: Perplexity (perplexity.ai)
- Announced: 2026-10-05T21:42:37+00:00
- Category: capability-change
- Coverage: not counted
- Announcement: yes
- Group: announcements
- Source: https://docs.perplexity.ai/docs/resources/changelog#october-2026
- Record: https://forck.live/items/16101-accurate-sandbox-extraction-usage-and-costs
- Subject: Sonar
- Models affected: openai/gpt-6-luna

Perplexity's Agent API now reports token usage and cost for sandbox extraction calls, broken down per model and including cache and reasoning-token dimensions. The update corrects response-level reporting without changing pricing or backfilling historical data.

## Evidence

Verbatim from https://docs.perplexity.ai/docs/resources/changelog#october-2026:

> Agent API responses now include model token usage and cost for successful pplx_sdk.llm.extract calls made inside the sandbox tool. Per-model tokens appear in usage.tool_calls_details.sandbox.token_usage.

---

Record: https://forck.live/items/16101-accurate-sandbox-extraction-usage-and-costs
Catalogue: https://forck.live/llms.txt
Current issue: https://forck.live/feed.md