LLM Gateway
Unified API gateway for LLM providers - route, secure, monitor, and optimize all your LLM traffic through a single endpoint.
Quick Start
Get up and running with the LLM Gateway in 4 steps.
Architecture
How the QuilrAI LLM Gateway processes every request - from your application to the LLM provider and back.
Features
12 items
HA & SLA
High availability endpoints, retry strategy, and latency guarantees for the QuilrAI LLM Gateway.
Integration Guide
Connect to the QuilrAI gateway in minutes - same SDK, one-line change.
UX Changelog
Recent interface improvements and quality-of-life changes.
Provider Support
Supported providers, API formats, and configuration details.
AWS Bedrock - Assume Role Setup
Configure an AWS Bedrock-backed API key using IAM role assumption instead of long-lived access keys. Applies to bedrock, anthropicmessagesbedrock, bedrockembeddings, and bedrockrerank providers.
AWS Bedrock - boto3 Runtime
Use the AWS SDK for Python (boto3) with QuilrAI guardrails by pointing the Bedrock Runtime client at the QuilrAI gateway.
OpenAI to Bedrock Translation
Use OpenAI-compatible chat clients with AWS Bedrock models. QuilrAI accepts an OpenAI-style /chat/completions request, calls Bedrock Converse or ConverseStream, and returns an OpenAI-shaped chat completion response.
LLM Gateway Log Export API
Use the Log Export API to read LLM Gateway request logs from your own data platform, SIEM, warehouse, or scheduled export job.