OpenViSTAI · Agents · Blockchain · Crypto
Submit a project
Menu
AI Infrastructure & Serving

AISIX

AISIX is a Rust-based server-side AI gateway and LLM proxy that exposes a unified OpenAI-compatible API for connecting applications to OpenAI, Anthropic, Gemini, DeepSeek and other OpenAI-compatible providers.

Explore the practical guide ↓

Independent OpenViST project profile, based on linked sources.

AISIX — OpenViST project profile in AI Infrastructure & Serving.
OpenViST project illustration. See the linked sources for product details.
Understand the project

Practical overview

When it fits

Use AISIX when an application needs a server-side layer between its callers and multiple supported model providers, especially when a common OpenAI-compatible interface and gateway-level controls are useful.

Who it is for

  • Teams building applications that need to connect to multiple LLM providers through a shared API interface.
  • Operators who need gateway-level API-key, model-access and rate-limit controls.
  • Developers who want a self-hosted gateway with an administration dashboard and observability integrations.

Documented uses

  • Send chat-completion or streaming requests to supported providers through a unified API.
  • Use embeddings through providers listed as supporting that capability.
  • Manage model and API-key records through the Admin API or dashboard.
  • Apply per-key model access rules, request validation and documented rate limits.
  • Inspect gateway activity using tracing, metrics and structured logs.
Before you choose

Requirements & limits

The project is open source under the Apache-2.0 license and documents a server-side deployment. The quick-start script launches AISIX with etcd through Docker Compose.

  • The documented provider list includes OpenAI, Anthropic, Gemini, DeepSeek and OpenAI-compatible providers; capability coverage differs by provider.
  • The provider matrix lists chat completions and streaming for all named providers, while embeddings are listed only for OpenAI, Gemini and OpenAI-compatible providers.
  • Configuration is backed by etcd; the quick-start procedure starts etcd with Docker Compose.
  • The documentation lists load balancing and fallback, cost tracking, semantic caching and additional providers as roadmap items.

Check current requirements in the official documentation. Source-based guidance does not mean OpenViST has run or independently tested this project.

Source-based practical guide

Start AISIX with the documented quick-start script

Launch AISIX with etcd using the project's quick-start procedure.

Before you start

  • A server environment with Docker Compose available.

Steps

  1. Run the project's quick-start shell script: the command below.

    Documented command
    curl -fsSL https://run.api7.ai/aisix/quickstart | sh

  2. The script downloads configuration files, generates a random admin key, and starts AISIX with etcd through Docker Compose.

  3. Use the documented local addresses for the Proxy API (http://127.0.0.1:3000), Admin API (http://127.0.0.1:3001/aisix/admin) and Admin UI (http://127.0.0.1:3001/ui).

Expected outcome

AISIX and etcd are started, with local proxy and administration interfaces available at the listed addresses.

Guide limitations

  • The quick-start description does not cover configuring a model or making a first request; consult the project's Quick Start documentation for those next steps.
Documentation 1 ↗
Evidence and transparency

Sources & review

Official repository ↗
Source record details
Source availability
Active
Sources checked
16 October 2026
Original website title
api7/aisix-archived · Official homepage title · retained in its source language
How we review sourcesSuggest a correction