AI GATEWAY for engineers

Develop & deploy AI with confidence

Analyze, evaluate, & monitor AI features in production. Just two lines of code to get started.

illustration of how to use Velvet's AI gateway with 2 lines of code
Trusted by innovative engineering teams

How it works

observe
Log requests
query
Analyze usage
Evaluate
Experiment & test
Data pipeline from OpenAI to Postgres
Ship quickly

Just 2 lines of code to get started

Warehouse every model request to your PostgreSQL database. Use logs to analyze, evaluate, and monitor AI features.

Website code snippet example of base URL
Code snippet of JSON object
analyze

Analyze & evaluate models

Store logs for short-term and long-term usage so you can analyze, run experiments, and continuously monitor AI features in production.

monitor

Continuous testing & experiments

Replay logs to run experiments, and sample production logs against metrics. Version models in production, and get alerts when your tests fail.

Backend workflows designed for engineers

Customer testimonial: Blaze AI

"We experiment with LLM models, settings, and optimizations. Velvet made it easy to implement logging, caching, and evals. And we're preparing training sets to eventually fine-tune our own models.

Chirag Mahapatra
Customer testimonial: Revo AI

"Velvet gives us a source of truth for what's happening between the Revo copilot, and the LLMs it orchestrates. We have the data we need to run evaluations, calculate costs, and quickly resolve issues."

Mehdi Djabri
CEO, Revo.pm
Customer testimonial: Find AI

"Our engineers use Velvet daily. It monitors AI features in production, even opaque APIs like batch. The caching feature reduces costs significantly. And, we use the logs to observe, test, and fine-tune."

Philip Thomas
CTO, Find AI
Use velvet

Flexible infrastructure for scale

table icon
Data interoperability

Log queryable requests to your DB. Secure and compliant.

code icon
Granular analysis

Query data with SQL to analyze usage, cost, and metrics.

sparkle icon
Intelligent caching

Optimize costs and latency with request caching.

graph icon
Evaluations framework

Replay logs against models, settings, and metrics to run experiments.

flag icon
Continuous monitoring

Sample logs in production against metrics, get alerts when they fail.

groupings icon
Dataset generation

Prepare datasets for fine-tuning and other training workflows.

AI gateway

Analyze, evaluate, and monitor your AI

Free up to 10k requests per month.

2 lines of code to get started.

Try Velvet for free

Q & A

Who is Velvet made for?
How do I get started?
Which models and DBs do you support?
What are common use cases?
How much does it cost?

Articles from Velvet

Engineering
Why Find AI logs OpenAI requests with Velvet

AI-powered B2B search engine logged 1,500 requests per second.

Engineering
Create a fine-tuning dataset for gpt-4o-mini

Use Velvet to identify and export a fine-tuning dataset.

Engineering
Cache LLM requests to reduce latency and costs

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