ACOG documentation

AI Cost Optimizer Gateway

An OpenAI- and Anthropic-compatible gateway in front of the AI providers you already use. It routes each request to the cheapest model that can do the job, caches what can be reused, and enforces your budgets, model access and data loss prevention rules.

Start with What is ACOG?

Get started

What ACOG is, how it saves money, and your first request in a few minutes.

Connect providers

Connect Anthropic, OpenAI, Google Vertex AI, AWS Bedrock, Azure OpenAI and custom endpoints, with keys or keyless.

Call the API

Base URLs, authentication, the compatible APIs, native provider routes, streaming, batches and errors.

Optimize cost

Auto mode, prompt caching, the semantic cache, batch routing and how savings are measured.

Govern and secure

Model access, budgets, rate limits, data loss prevention and prompt injection protection.

Administer

Users, teams, single sign-on, keys, webhooks, observability, notifications and billing.

Self-hosted

Run ACOG in your own environment: requirements, installation, configuration, licensing and upgrades.

Reference

Roles and permissions, error codes, response headers and a glossary.

For language models and AI assistants: llms.txt (an index of every page as Markdown) and llms-full.txt (all of the ACOG documentation in one file).