Integrations
AISIX integrates with developer tools and application frameworks by replacing the upstream provider endpoint, provider API key, and provider model name with AISIX gateway values. The client keeps its native request shape, while AISIX owns authentication, model aliasing, provider credentials, policy, and telemetry at the gateway boundary.
Use these guides for clients that can send requests to a custom API endpoint, including clients that use OpenAI-compatible Chat Completions, the OpenAI Responses API, or Anthropic-compatible traffic.
This pattern lets teams adopt AISIX without rewriting application code or changing the coding tool itself. The client keeps using its familiar SDK, CLI, or framework, while gateway policy, routing, observability, and provider credentials move into AISIX.
How Integrations Use AISIX
Most integrations use the same three AISIX values:
- The proxy API base URL.
- A caller API key.
- A model alias that the caller API key can access.
Many clients describe the third value as a custom model, model ID, model name, or public model name. In AISIX, use the model alias for that field. AISIX authenticates the caller key, resolves the alias to an upstream provider configuration, applies configured policies, and records gateway telemetry.
Integration Types
| Client type | Use when | Guides |
|---|---|---|
| Coding agents | A local editor, AI CLI, remote development environment, or automation job should send requests through AISIX. | Coding Agents |
| Frameworks | An application framework should call AISIX from application code. | LangChain, LlamaIndex, Vercel AI SDK, Instructor |
Prerequisites
Each integration guide assumes the gateway already has the resources needed for the client path:
- A caller API key for the application, developer, or automation profile.
- A model alias that the caller API key can access.
- A proxy API route compatible with the client, such as OpenAI-compatible Chat Completions, the OpenAI Responses API, or Anthropic Messages.
If you have not created these resources yet, start with Self-Hosted Quickstart, OpenAI SDK Quickstart, or Anthropic SDK Quickstart.
Next Steps
- Coding Agents: route AI coding tools through AISIX.
- LangChain: connect LangChain applications to AISIX.
- LlamaIndex: connect LlamaIndex applications to AISIX.
- Vercel AI SDK: connect TypeScript applications using Vercel AI SDK.
- Instructor: route structured-output requests through AISIX.
- Supported Endpoints: review the proxy API families available to clients.