Evaluations
Measure model quality.
What it does
Measure model quality.
- Inference
- Fine-tuning
- GPU clusters
- Model shaping
- Pre-training
- Category
- AI evaluation and observability
- Users
- AI-native teams, Enterprise developers, Production AI workloads
- Public API
- Not offered
Not yet disclosed: deployment options, platforms, languages and support channels.
Pricing
- Free plan$0
Free trial on paid plans
Prices as published by Together AI, checked Oct 2026.
Security and compliance
As reported by Together AI. Ask for audit reports before you buy.
- SOC 2 Type IICompliant
- Zero data retention (ZDR): Together does not store inputs or outputs by default; temporary caching may be used for performance unless otherwise configured.
- Training opt-in: Data sharing for training other models is opt-in and not enabled by default; configurable in Organization Settings under Privacy.
- Organization-level privacy toggles: Admins can control storing prompts/responses, allowing data for training, and allowing passthrough models.
- Passthrough model isolation: Non-passthrough models run on Together's own infrastructure with no call-out to model authors; passthrough is a separate organization-level toggle.
- VPC-based deployments and private networking available for enterprise customers.
- OIDC authentication supported for GPU Clusters.
- Single sign-on (SSO) listed under Administration features.
Reviews
No reviews yet
Reviews come from people who use Evaluations at work. Share how your team uses it to help other buyers decide.
Alternatives
Market Rush
by Olam Labs
Market battle royale trading game where firms use leverage, options, and email across six quarters; highest net worth at close wins.
DataCenterBench
by Robocurve
Evaluating robots on data-center construction tasks, including racking servers, routing cable, and the physical work behind the compute supply chain.
ML observability
by Openlayer
Continuously track performance, drift, and live issues with automated observability for ML systems.
Clarity
by Guide Labs
The first inherently interpretable AI platform, including PromptConceptTraining to understand which part of the prompt is responsible for the output.
Web-based AI simulation platform to build, evaluate, and test AI agents against realistic scenarios and custom metrics.
Observability
by Mastra
AI observability platform that captures metrics, logs, and traces for every agent run in production.
Is this your product?
Claim it to keep details accurate and submit evidence for the next ranking review.
Claim Evaluations