
Overview
The AI Gateway works as a standalone product or alongside your existing Aptible infrastructure. No apps or databases required. Sign up and start sending requests right away. See the pricing page for plan and usage details.
- Access 400+ models across Claude, GPT, Nova, Llama, Qwen, and more through a single API
- Govern which models your team can use with environment-level model access policies
- Control and monitor spend with organization-wide limits, plus per-environment and per-key cost visibility
- Review request history and inspect full request and response logs to troubleshoot and refine prompts
- Drain traces to Langfuse for deeper observability
- Send PHI safely under Aptible’s HIPAA BAA, with automatic audit logging and encryption
Get Started
Create your first LLM key
Step-by-step guide covering key creation, initial setup, and the LLM Gateway’s core features.
Supported Models
The AI Gateway supports 400+ models across Claude, GPT, Nova, Llama, Qwen, and more. See Supported Models for full details.Claude
bedrock/anthropic Haiku, Sonnet, and OpusGPT & o-series
openai GPT-4o, GPT-4.1, GPT-5, o3, o4Nova, Llama, Qwen & more
bedrock Amazon Nova, Meta Llama, Qwen & moreFeatures
Model Access Policies

Cost Visibility & Control

Audit Logging


