Disclosure: I work on Xisu AI. This post was drafted with AI assistance and reviewed by our team.
The most common API integration problem is not the model. It is a client that still points to the original provider’s endpoint while using a key from somewhere else.
If your client supports the OpenAI API format, connecting it to Xisu AI usually requires only three changes: create a key, set the compatible base URL, and select a model available in the model marketplace. Your application logic can remain unchanged.
This guide shows the setup and a practical way to diagnose the failures that tend to appear during the first request.
What you need before changing code
Xisu AI provides an API gateway for models from multiple providers, including OpenAI, Anthropic, Google, DeepSeek, Qwen, Moonshot, Zhipu, xAI, Meta, Baidu, ByteDance, Tencent, NVIDIA, and MiniMax.
The exact model names and prices should be checked in the Xisu AI model marketplace. Do not copy a model identifier from an unrelated provider and assume it is available. The request should use the model name shown in the marketplace.
Before configuring your client:
- Register on Xisu AI.
- Add balance to your account.
- Create an API key in the dashboard.
- Save the key immediately. The plain-text key is shown only once when it is created.
- Confirm that the selected model is available in the model marketplace.
Xisu AI charges based on actual token usage. Requests are settled after the call rather than pre-charged, and usage is recorded in the request logs.
The one setting that usually matters
For an OpenAI-compatible client, use this base URL:
https://api.xisu.ai/v1
The important detail is the /v1 suffix. Many clients construct paths such as /chat/completions automatically. If you provide the wrong base URL, the client may send the request to an endpoint that does not belong to the compatible API.
A typical configuration concept looks like this:
- API key: the key created in the Xisu AI dashboard
- Base URL:
https://api.xisu.ai/v1 - Model: an exact model name listed in the Xisu AI model marketplace
If your client has separate fields for “API endpoint” and “API version,” do not add an extra version segment unless the client requires it. The base URL above already includes the compatible API version.
The compatible API exposes chat completions, embeddings, model listing, and image generation endpoints. Image generation is supported, but image editing and variations are not. Voice-related endpoints are not currently open.
A low-risk way to test the connection
Do not start by changing your production application. First, make one small request from the same client or command-line coding tool that you intend to use.
Use this sequence:
- Enter the Xisu AI API key.
- Set the base URL to
https://api.xisu.ai/v1. - Select one exact model name from the model marketplace.
- Send a short request with minimal input.
- Check whether the response returns normally.
- Open the request log and compare the model name, token count, and cost.
The request log is useful because it lets you verify what actually happened, rather than relying only on the client’s displayed provider name. Each call records the requested model, token usage, and cost. You can also use the request_id to inspect an individual request.
This is especially helpful when a desktop client displays a generic “AI provider” label or when a wrapper library silently applies its own defaults.
Troubleshooting checklist
The request is rejected immediately
Check the following in order:
- Is the API key copied correctly?
- Did you save the key when it was created?
- Is the client using
https://api.xisu.ai/v1as its base URL? - Is there an accidental extra path after
/v1? - Is the account balance above zero?
- Does the selected model name exactly match the model marketplace?
When the balance reaches zero, new requests are rejected. Your key and configuration remain available, and requests can resume after the balance is topped up.
The client says the model is unavailable
Do not substitute a similar-looking model name. First open the model marketplace and copy the exact available name. Model availability and pricing are defined there, and the gateway executes the model you request rather than silently replacing it with another one.
If you need to confirm that the request reached the intended model, inspect the request log and compare the recorded model name with the one configured in your client.
The cost looks different from your estimate
Xisu AI bills according to actual token usage. Review the request log for the token count and final cost. Amounts are calculated to ten decimal places, so a small request can produce a very precise charge.
A useful habit is to record the request_id during testing. That gives you a specific item to check when comparing application behavior with dashboard usage.
You need separate limits for separate projects
Create multiple keys and assign each one its own budget limit. This is useful for separating development, production, internal tools, or different team projects. If one key reaches its limit, it does not affect the other keys.
Keys can also be revoked at any time, with the change taking effect immediately.
When OpenAI compatibility is not enough
If you are using Claude Code or an Anthropic-native integration, Xisu AI also supports the Anthropic protocol. Set:
ANTHROPIC_BASE_URL=https://api.xisu.ai
The same key and the same account balance work across the OpenAI-compatible and Anthropic protocols. This means you can switch protocol-specific clients without moving funds or creating a separate account.
For most existing applications, however, the OpenAI-compatible configuration is the shortest path: preserve the application code, change the base URL, use the correct key, and select a model listed in the marketplace.
Try it
If you want to test the setup, start with a small request and verify the resulting log entry before integrating it into a larger project.
Top comments (0)