Scalix AI

Scalix AI delivers LLM inference through one OpenAI-compatible API — a free default tier plus a third-party pass-through catalog, with tool use, and vision.

Overview

Scalix AI provides LLM inference through an OpenAI-compatible API. Omitting the model gets you the free default tier (scalix-auto/free); the third-party pass-through catalog (scalix-gw/<vendor>/<model> ids) adds frontier models — all behind one endpoint with unified authentication, cost controls, and usage tracking. Routing is fail-closed: the model id you send is what runs, with no silent fallback.

Quick Start

bash

scalix-cloud ai infer "Explain quantum computing in one sentence" --model scalix-auto/free

The prompt is a positional argument; pass the model with --model.

REST API

The API is OpenAI-compatible — existing code works with a URL change:

bash

curl -X POST https://api.scalix.world/v1/ai/chat/completions \
  -H "Authorization: Bearer $SCALIX_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "scalix-auto/free",
    "messages": [
      {"role": "user", "content": "What is Scalix Cloud?"}
    ]
  }'

Streaming

bash

curl -X POST https://api.scalix.world/v1/ai/chat/completions \
  -H "Authorization: Bearer $SCALIX_API_KEY" \
  -d '{
    "model": "scalix-auto/free",
    "messages": [{"role": "user", "content": "Write a haiku"}],
    "stream": true
  }'

SDK

The request/response envelope is OpenAI-compatible; the SDK exposes it as the chatCompletion function:

typescript

import { chatCompletion } from "@scalix-world/sdk";
 
const { data, error } = await chatCompletion({
  body: {
    model: "scalix-auto/free",
    messages: [{ role: "user", content: "Hello!" }],
  },
});
 
if (data) console.log(data.choices[0].message.content);

Streaming

streamChatCompletion posts to /v1/ai/chat/completions/stream and the response is server-sent events — pass parseAs: "stream" to consume the raw stream (see the TypeScript SDK guide for details):

typescript

import { streamChatCompletion } from "@scalix-world/sdk";
 
const { response } = await streamChatCompletion({
  body: {
    model: "scalix-auto/free",
    messages: [{ role: "user", content: "Write a story" }],
  },
  parseAs: "stream",
});

Available Models

List the live catalog at any time:

bash

scalix-cloud ai models

Model	Best for	Availability
`scalix-auto/free`	The free default tier — omit `model` or pass it explicitly	Available
`scalix-gw/<vendor>/<model>`	Third-party pass-through catalog: frontier models from OpenAI, Anthropic, Google, DeepSeek, Qwen, x-ai, Moonshot, Z.ai and more, at pass-through pricing	Available

scalix-auto/free is the default — requests that omit model use it. Catalog ids are browseable with scalix-cloud ai models or GET /v1/ai/models; every id in the response is callable, and third-party catalog requests are routed through OpenRouter to the model provider. Embeddings run as a built-in platform service (powering ScalixNova vector search, Enclave, and semantic features) — every plan includes them; there is no separate embedding model to select.

All AI usage is billed per-token from your credit pool. See Billing for per-model rates.

Features

Tool/Function calling: Full support for OpenAI-compatible tool use
Vision: Multi-modal inputs (images + text)
Streaming: Token-by-token streaming with metering
Cost controls: Per-key spending limits and model allowlists
Usage tracking: Token counts and cost attribution per request