Archive

Velvet is now part of Arize

Velvet is now part of Arize

Acquisition to accelerate developer-first AI infrastructure

LLM evaluations: Experiments & Monitoring

LLM evaluations: Experiments & Monitoring

Run one-time and ongoing evaluations with Velvet

Monitor AI features in production

Monitor AI features in production

Ongoing tests of LLM-powered features + weekly email updates

Evaluate models, settings, and metrics

Evaluate models, settings, and metrics

Experiments and continuous monitoring

Run model evaluations with Velvet

Run model evaluations with Velvet

Beta test our new experiments workflow

How to use data to optimize AI apps

How to use data to optimize AI apps

Tutorial on cost attribution, evaluations, and fine-tuning

Query LLM logs with text-to-SQL

Query LLM logs with text-to-SQL

Free up to 100k requests per month

New dashboard analytics this week

New dashboard analytics this week

Just 2 lines of code to get started

Velvet on Product Hunt 🚀

Velvet on Product Hunt 🚀

Try our new AI Gateway, launching today

New: OpenAI Batch & Anthropic Messages APIs

New: OpenAI Batch & Anthropic Messages APIs

The latest from Velvet's AI gateway

Velvet latency benchmarks

Velvet latency benchmarks

Plus, improve response times by 50% with caching

Add LLM caching to your app

Add LLM caching to your app

Return results in milliseconds and don't waste calls on identical requests

FirstBack
123
Next Last