Primary Infrastructure: Mascot, NSW 2020, Australia

OpenAI-Compatible API Gateway

Low-latency, OpenAI-compatible AI model inference gateway for developer applications, AI agents, and IDE tools. Hosted locally in Mascot, NSW, Australia.

API Base URL

https://api.aicompute.au/v1

SSL / TLS 1.3 Active

Quick-Start Integration & Developer Tools

Select your programming language or AI coding tool below for copyable setup instructions.

from openai import OpenAI

client = OpenAI(
    base_url="https://api.aicompute.au/v1",
    api_key="dk_live_your_api_key_here"
)

response = client.chat.completions.create(
    model="glm-5",
    messages=[{"role": "user", "content": "Hello from Mascot, Australia!"}],
    stream=True
)

for chunk in response:
    if chunk.choices[0].delta.content:
        print(chunk.choices[0].delta.content, end="")

import OpenAI from 'openai';

const openai = new OpenAI({
  baseURL: 'https://api.aicompute.au/v1',
  apiKey: 'dk_live_your_api_key_here',
});

async function main() {
  const stream = await openai.chat.completions.create({
    model: 'glm-5',
    messages: [{ role: 'user', content: 'Hello!' }],
    stream: true,
  });

  for await (const chunk of stream) {
    process.stdout.write(chunk.choices[0]?.delta?.content || '');
  }
}

main();

curl https://api.aicompute.au/v1/chat/completions \
  -H "Authorization: Bearer dk_live_your_api_key_here" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "glm-5",
    "messages": [{"role": "user", "content": "Hello!"}],
    "stream": true
  }'

Add AiCompute to ~/.config/opencode/config.json:

{
  "providers": {
    "aicompute": {
      "npm": "@opencode/openai",
      "name": "AiCompute.au",
      "options": {
        "baseURL": "https://api.aicompute.au/v1",
        "apiKey": "dk_live_your_key_here"
      },
      "models": {
        "glm-5.2": { "name": "GLM-5.2" },
        "glm-5": { "name": "GLM-5" },
        "Gemmoz-1m": { "name": "Gemmoz 1M" },
        "gpt-oss-120b": { "name": "GPT OSS 120B" },
        "gemma-4-31b-it": { "name": "Gemma 4 31B" }
      }
    }
  }
}

Set environment variables or edit ~/.pi/agent/models.json:

# Option 1: Shell Environment Variables
export OPENAI_BASE_URL="https://api.aicompute.au/v1"
export OPENAI_API_KEY="dk_live_your_key_here"

# Option 2: Add Provider in ~/.pi/agent/models.json
{
  "providers": {
    "aicompute": {
      "baseUrl": "https://api.aicompute.au/v1",
      "apiKey": "dk_live_your_key_here",
      "apiType": "openai"
    }
  }
}

Export environment variables in your terminal:

export OPENAI_BASE_URL="https://api.aicompute.au/v1"
export OPENAI_API_KEY="dk_live_your_key_here"

# Execute Codex CLI
codex --model glm-5 "Write unit tests for auth middleware"

Configure Claude Code via environment variables:

export ANTHROPIC_BASE_URL="https://api.aicompute.au/v1"
export ANTHROPIC_API_KEY="dk_live_your_key_here"

# Execute Claude Code
claude --model glm-5 "Refactor database queries"

Supported Models & Rates

Billed per 1M tokens with a 20% discount applied below standard Vertex AI rates.

Model Name	Input / 1M (AUD)	Cached / 1M (AUD)	Output / 1M (AUD)	Status
gemma-4-26b-a4b-it	$0.0420	$0.0210 hit	$0.2200	Active
glm-5	$0.6000	$0.3000 hit	$1.9200	Active
gpt-oss-120b	$0.0300	$0.0150 hit	$0.1700	Active
gemma-4-31b-it	$0.0900	$0.0450 hit	$0.3400	Active
glm-5.2	$0.4872	$0.2436 hit	$1.5310	Active
gemmoz-1m	$0.6000	$0.3000 hit	$1.9200	Active

API Endpoints

POST /v1/chat/completions

Generates model responses for chat interactions. Supports SSE streaming when "stream": true.

GET /v1/models

Retrieves the list of active models enabled for your API key.