AI GATEWAY for engineers

Develop & deploy AI with confidence

Log requests to your DB, optimize, and run experiments. 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
OPTIMIZE
Run experiments
Data pipeline from OpenAI to Postgres
easy onboarding

Add 2 lines of code to get started

Warehouse every OpenAI and Anthropic request to your PostgreSQL database. Use logs to analyze, evaluate, and generate datasets.

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

Analyze usage & run experiments

We store a customizable JSON object so you can granularly monitor usage, calculate cost, run evaluations, and fine-tune models.

reduce costs

Optimize with caching & batching

Enable caching to reduce costs and latency. Get full transparency into OpenAI's Batch and Files APIs using our built-in proxy support.

code snippet for enabling caching in the header

Backend workflows designed for engineers

Customer testimonial: Blaze AI

"We experiment with LLM models, settings, and optimizations. Velvet made it easy to implement logging and caching. And we're storing 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
Full data ownership

Log every request to your database. Secure and compliant.

code icon
Granular observability

Store data as JSON to gain deep insights into usage, costs, and more.

graph icon
Powerful analysis

Understand API usage to optimize AI features and resolve problems.

flag icon
Intelligent caching

Reduce costs and latency with our smart caching system.

sparkle icon
Experiment framework

Run experiments on test datasets to optimize outputs at scale.

groupings icon
Dataset generation

Export datasets for fine-tuning models and other batch workflows.

AI gateway

Analyze and optimize your AI features

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.