[KongchangAI]
Product

Xisu AI

A multi-provider API gateway for AI models that is compatible with the OpenAI API format and provides unified access to models from vendors including OpenAI, Anthropic, Google and DeepSeek. It offers request logging and token-based billing.

Timeline (last 90 days)

Oct 18

Xisu AI provides an API gateway for multi-provider models, covering OpenAI, Anthropic, Google, DeepSeek, Qwen, Moonshot, Zhipu, xAI, Meta, Baidu, ByteDance, Tencent, NVIDIA, MiniMax, and others.

Unverified50%
Oct 18

For OpenAI-compatible clients, Xisu AI's base URL should be set to https://api.xisu.ai/v1, and the /v1 suffix is a key detail, since many clients automatically append paths such as /chat/completions.

Unverified50%
Oct 18

Xisu AI's OpenAI-compatible API exposes chat completions, embeddings, model list, and image generation endpoints; image generation is supported, but image editing and variations are not, and voice-related endpoints are not yet available.

Unverified50%
Oct 18

Xisu AI supports the Anthropic protocol; set ANTHROPIC_BASE_URL=https://api.xisu.ai to connect Claude Code or native Anthropic integrations.

Unverified50%
Oct 18

With Xisu AI, the same key and the same account balance work across the OpenAI-compatible protocol and the Anthropic protocol, so switching between protocol-specific clients requires no fund transfer or separate account.

Unverified50%
Oct 18

Xisu AI bills by actual token usage, charging after the request completes, with usage recorded in the request log; amounts are calculated to ten decimal places.

Unverified50%
Oct 18

When an Xisu AI account balance reaches zero, new requests are rejected, but the key and configuration are retained and service resumes after topping up.

Unverified50%
Oct 18

The Xisu AI gateway executes the model requested by the user and does not silently substitute another model.

Unverified50%
Oct 18

Xisu AI's request log records the timestamp, requested model, input/output token counts, cost, and a unique request_id for each call, which can be used to verify model names and billing.

Unverified50%
Oct 18

Xisu AI allows creating multiple API keys and assigning an independent budget cap to each key; one key reaching its limit does not affect other keys, and keys can be revoked at any time with changes taking effect immediately.

Unverified50%

2 more timeline events

All Facts (12)

Unverified

Xisu AI provides an API gateway for multi-provider models, covering OpenAI, Anthropic, Google, DeepSeek, Qwen, Moonshot, Zhipu, xAI, Meta, Baidu, ByteDance, Tencent, NVIDIA, MiniMax, and others.

50%
Unverified

For OpenAI-compatible clients, Xisu AI's base URL should be set to https://api.xisu.ai/v1, and the /v1 suffix is a key detail, since many clients automatically append paths such as /chat/completions.

50%
Unverified

Xisu AI's OpenAI-compatible API exposes chat completions, embeddings, model list, and image generation endpoints; image generation is supported, but image editing and variations are not, and voice-related endpoints are not yet available.

50%
Unverified

Xisu AI supports the Anthropic protocol; set ANTHROPIC_BASE_URL=https://api.xisu.ai to connect Claude Code or native Anthropic integrations.

50%
Unverified

With Xisu AI, the same key and the same account balance work across the OpenAI-compatible protocol and the Anthropic protocol, so switching between protocol-specific clients requires no fund transfer or separate account.

50%
Unverified

Xisu AI bills by actual token usage, charging after the request completes, with usage recorded in the request log; amounts are calculated to ten decimal places.

50%
Unverified

When an Xisu AI account balance reaches zero, new requests are rejected, but the key and configuration are retained and service resumes after topping up.

50%
Unverified

The Xisu AI gateway executes the model requested by the user and does not silently substitute another model.

50%
Unverified

Xisu AI's request log records the timestamp, requested model, input/output token counts, cost, and a unique request_id for each call, which can be used to verify model names and billing.

50%
Unverified

Xisu AI allows creating multiple API keys and assigning an independent budget cap to each key; one key reaching its limit does not affect other keys, and keys can be revoked at any time with changes taking effect immediately.

50%
Unverified

An Xisu AI API key's plaintext is shown only once at creation and must be saved immediately.

50%
Unverified

For most existing applications, the OpenAI-compatible configuration is the shortest path to Xisu AI: keep the application code, change the base URL, use the correct key, and select a model listed in the marketplace.

50%

Source Articles