PulseAugur
EN
LIVE 20:26:25

Lookspan bills reasoning tokens separately for AI models

Lookspan has updated its billing system to specifically track and charge for reasoning tokens. This change ensures that if a model's pricing includes a distinct rate for reasoning, those specific tokens will be billed accordingly, preventing double-charging with general output tokens. The update aims to provide more precise cost-per-span calculations for models that utilize reasoning capabilities. AI

IMPACT Provides more accurate cost tracking for AI model usage, aiding operators in managing expenses.

RANK_REASON This is a product update for an observability tool, not a core AI release or significant industry event.

Read on Mastodon — fosstodon.org →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. Mastodon — fosstodon.org TIER_1 English(EN) · [email protected] ·

    Lookspan now bills reasoning tokens at their own rate. If your model pricing sets a reasoning rate, reasoning tokens (a subset of output, OpenAI o-series style)

    Lookspan now bills reasoning tokens at their own rate. If your model pricing sets a reasoning rate, reasoning tokens (a subset of output, OpenAI o-series style) are charged at it instead of the output rate — no double-charging. More accurate cost-per-span for reasoning models. ht…