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