Docs

API quick start

AITransX accepts OpenAI-compatible chat completion requests. Use your aitx key as a Bearer token.

Authentication

Every private request must include your API key. Create and manage keys from the dashboard.

HTTP

Authorization: Bearer aitx-your-key
Content-Type: application/json

Base URL

Use AITransX as the OpenAI SDK base URL, then keep the same chat completion request shape you already use.

OpenAI SDK

base_url = "https://aitransx.com/v1"

Chat completions

Send requests to /v1/chat/completions. Streaming is supported with "stream": true.

cURL

curl https://aitransx.com/v1/chat/completions \
  -H "Authorization: Bearer aitx-your-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "auto",
    "messages": [{"role": "user", "content": "Hello"}],
    "stream": false
  }'

Model IDs

Use auto for default routing, or copy an exact model ID from the model catalog or GET /v1/models.

Models

GET https://aitransx.com/v1/models

model = "auto"
model = "openai/gpt-4o"
model = "deepseek/deepseek-chat"

Streaming responses

Set stream to true to receive OpenAI-compatible server-sent events for chat output.

JSON

{
  "model": "auto",
  "messages": [{"role": "user", "content": "Hello"}],
  "stream": true
}

Python SDK

Use the OpenAI SDK and change only the base URL.

Python

from openai import OpenAI

client = OpenAI(
    api_key="aitx-your-key",
    base_url="https://aitransx.com/v1",
)

resp = client.chat.completions.create(
    model="auto",
    messages=[{"role": "user", "content": "Hello"}],
)

Logs and privacy

Dashboard logs keep operational metadata such as model, provider, tokens, latency and status. Prompt and response bodies are not written to disk.

Public endpoints

Endpoint	Purpose	Auth
`GET /v1/models`	List routable model IDs	No key required
`GET /api/pricing`	List public model prices	No key required
`POST /v1/chat/completions`	Create a chat completion	Bearer key
`GET /healthz`	Service health check	No key required