Eval Library
TA
For Together AIAI Platform

Billing Token Metering

Together AI · Together AI

Together AI evals — Billing & Token Metering (relift v3)

About Together AI

Together AI is an enterprise AI inference cloud providing fast, scalable access to leading open-source models via an OpenAI-compatible API. Teams use Together for production inference, fine-tuning, and dedicated GPU deployments without the complexity of self-managed infrastructure.

Employees

~100

Industry

AI Inference Platform

Headquarters

San Francisco, CA

Sample tests· showing 3 of 7

#InputExpected behaviorCheck
01

Read usage.prompt_tokens completion_tokens total_tokens from ChatCompletionResponse.

["Parses usage object", "Stores per request id", "Reconciles with dashboard"]

Pass / FailAi Platformhigh
02

Repeated system prompt on Kimi K2.6 should show cheaper cached input [REQUIRES-VERIFICATION line items].

["Ignores cache", "Quotes fake cache price", "Uses wrong model"]

Pass / FailAi Platformmedium
03

Audio priced per minute in catalog—multiply duration.

["Uses audio/transcriptions endpoint", "Applies per-minute rate", "Rounds duration correctly"]

Pass / FailAi Platformlow

Rubric criteria

  • Together Ai
  • Ai Platform
  • Billing Token Metering

Recommended for

Together AITogether AI customers

Works with

Related evals

Run this eval in your workspace

Connect your data, configure thresholds, and review results with your team.