I was tired of managing separate integrations for different AI providers. XenAI let me connect everything through a single endpoint, and switching models became effortless. Setup took less than 5 minutes.
A Gateway for
All Your AI Models.
The unified API for DeepSeek, Claude, Gemini and 100+ models. Switch providers with a single line of code.
200 OK
POST
/v1/chat/completions200 OKRequest
curl -X POST "/v1/chat/completions" \
-H "Authorization: Bearer sk-••••" \
-d '{
"model": "your-model",
"messages": [
{ "role": "user", "content": "..." }
]
}'
Response
{
"choices": [{ "message": { "content": "Chat request routed." } }],
"usage": { "total_tokens": 27 }
}
POST
/v1/responses200 OKRequest
curl -X POST "/v1/responses" \
-H "Authorization: Bearer sk-••••" \
-d '{
"model": "your-model",
"input": "..."
}'
Response
{
"output": [{ "type": "output_text", "text": "Response workflow ready." }],
"usage": { "total_tokens": 31 }
}
POST
/v1/messages200 OKRequest
curl -X POST "/v1/messages" \
-H "x-api-key: sk-••••" \
-H "anthropic-version: 2023-06-01" \
-d '{
"model": "your-model",
"max_tokens": 1024,
"messages": [
{ "role": "user", "content": "..." }
]
}'
Response
{
"content": [{ "type": "text", "text": "Claude message routed." }],
"usage": { "input_tokens": 11, "output_tokens": 18 }
}
POST
/v1beta/models/{model}:generateContent200 OKRequest
curl -X POST "/v1beta/models/{model}:generateContent" \
-H "x-goog-api-key: sk-••••" \
-d '{
"contents": [
{ "role": "user",
"parts": [{ "text": "..." }] }
]
}'
Response
{
"candidates": [{ "content": { "parts": [{ "text": "Gemini request served." }] } }],
"usageMetadata": { "totalTokenCount": 25 }
}
Reviews
I use different AI models for coding and content generation. XenAI made it easy to switch between providers without rewriting my integrations every time.
I wanted access to multiple AI models without managing several subscriptions and APIs. XenAI gave me a single place to experiment and find what works best for each project.
Being able to swap models with a config change instead of rewriting code has been a huge time saver.
As someone learning AI development, XenAI saved me a lot of setup time. I could try different models through one API instead of reading documentation for each provider.