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.
Sample tests· showing 3 of 7
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 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
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.