Introduction

One OpenAI-compatible API for 80+ AI models — chat, images, speech and embeddings — intelligently orchestrated with automatic failover, metered to actual usage and billed from a single wallet.

You call one endpoint with one key. AIx selects a healthy route for the requested model, fails over automatically when a route is unavailable, meters real usage and charges a prepaid wallet shared across the whole theaimart platform.

Why AIx

OpenAI-compatible — point any OpenAI SDK at our base URL; nothing to relearn.
Intelligent orchestration — capability-aware routing with automatic failover.
Measured pay-per-use — prepaid credits settled to actual token or unit usage. No subscriptions or minimums.
One wallet & identity — the same account and credits work across theaimart.co and adx.
Coding-first — top coding models curated, low-latency routing, embeddings for code search.
Zero prompt retention — we store model + token counts + cost, never your prompts or outputs.

Base URL

All OpenAI-compatible endpoints live under:

https://api.aix.theaimart.co/v1

Your first request

Create a key in the dashboard, then:

curl https://api.aix.theaimart.co/v1/chat/completions \
  -H "Authorization: Bearer $AIX_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "deepseek-ai/DeepSeek-V3.2",
    "messages": [{ "role": "user", "content": "Hello, AIx" }]
  }'

from openai import OpenAI

client = OpenAI(base_url="https://api.aix.theaimart.co/v1", api_key="$AIX_KEY")
resp = client.chat.completions.create(
    model="deepseek-ai/DeepSeek-V3.2",
    messages=[{"role": "user", "content": "Hello, AIx"}],
)
print(resp.choices[0].message.content)

Tip: switch models by changing one string — the request shape never changes. Browse the catalog in Models.

What’s next

Authentication — keys and headers
Chat completions — the core endpoint
Messages API — Anthropic-compatible clients and agents
SDKs & integrations — Cursor, Cline, LangChain and more

Authentication →