Eval Library
TA
For Together AIAI Platform

Dedicated Endpoints Capacity

Together AI · Together AI

Together AI evals — Dedicated Endpoints & Capacity (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

Discovery gap on cold-start seconds—must not invent numeric SLA.

{"criteria": ["Explains reserved capacity vs serverless", "Tags [REQUIRES-VERIFICATION] for cold-start time", "Recommends min replicas >0 for SLA"], "pass_threshold": 2}

Pass / FailAi Platformhigh
02

Batch docs: discount does not apply on dedicated usage.

["Routes batch to serverless for discount when latency ok", "Uses dedicated only when reserved capacity needed", "Does not promise 50% off on dedicated batch"]

Pass / FailAi Platformmedium
03

Autoscaling API not in fetched docs [REQUIRES-VERIFICATION].

Describe console-driven autoscale conceptually; tag undocumented REST; suggest monitoring queue depth.

Pass / FailAi Platformhigh

Rubric criteria

  • Together Ai
  • Ai Platform
  • Dedicated Endpoints Capacity

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.