# AuCore — full documentation for agents
> Generated from ai.aunuhost.bond on 2026-09-03. This file mirrors llms.txt but inlines the body of every primary page.
Canonical index: https://ai.aunuhost.bond/llms.txt
OpenAPI 3.1: https://ai.aunuhost.bond/openapi.json
---
# AuCore — One API for every frontier model
> AuCore is a single OpenAI-compatible API for 500+ language models. Plan-based priority routing, per-account keys, and full usage analytics.
Source: https://ai.aunuhost.bond/
0
Models available
0
Median routing overhead
0
Uptime, last 30 days
0
Priority tiers
Quickstart
## Change two lines. Keep your code.
AuCore speaks the OpenAI chat completion format, so any existing client
works. Swap the base URL and key, then choose any model in the catalog.
Works withOpenAI SDK · LangChain · AI SDK · curl
SupportsStreaming · vision · tool calling
AuthBearer token, one key per account
[Full documentation →](https://ai.aunuhost.bond/docs)
main.py
Platform
## Everything you need to run models in production
Built for teams that care about cost control, observability and predictable latency.
Pricing
## Priority scales with your plan
Every plan reaches the same catalog. Higher tiers get more throughput and are dispatched ahead of lower tiers
when demand peaks.
All prices in IDR per month. [Compare plans in detail →](https://ai.aunuhost.bond/plan)
Catalog
## Popular models right now
Copy any model ID and use it immediately in your request body.
[Browse all models →](https://ai.aunuhost.bond/model)
| Model | Provider | Context | Best for | Min plan | |
| --- |--- |--- |--- |--- |--- |
Market
## BTC / USD — live
Real-time Bitcoin price from TradingView. Crypto pricing data also available via the
[REST toolkit](https://ai.aunuhost.bond/restapi) (`info/crypto`, `finance/gold-price`).
## Start building today
Request a key, redeem it, and your
dashboard is live in under a
minute.
[Request a key](https://ai.aunuhost.bond/support)[Try the playground](https://ai.aunuhost.bond/playground)
### Get AuCore updates
New features, model drops and promos — a few emails a month, no
spam. Unsubscribe any time.
---
# Documentation — AuCore
> How to get an AuCore API key and use it: authentication, models, chat completions, streaming, token optimization and error handling.
Source: https://ai.aunuhost.bond/docs
Documentation
# Getting started
AuCore exposes one OpenAI-compatible API for every model in the catalog.
If your code already talks to OpenAI, you only need to change two values.
AI API — Base URL
This is the value you set as `base_url` in the OpenAI SDK (or any
compatible client). Both and resolve.
## 1. Get a key
1. Choose a plan on the [pricing page](https://ai.aunuhost.bond/plan).
2. Request access on the [support page](https://ai.aunuhost.bond/support), naming your plan.
3. AuCore issues your key and sends it to you.
4. Redeem it at [/login](https://ai.aunuhost.bond/login). Your [dashboard](https://ai.aunuhost.bond/client) then shows the key, base URL and analytics.
Keys look like `auc_live_a1b2c3d4e5f6g7h8`. They are account-scoped, rotatable and revocable at any time.
## 2. Two APIs — which one do I use?
AuCore runs **two independent API planes**, each with its own key type, base URL and quota system. Pick the one that matches what you're building:
| | 🤖 AI API (this page) | 🧰 REST API Toolkit ([catalog](https://ai.aunuhost.bond/restapi)) |
| --- |--- |--- |
| **What it does** | Chat completions, embeddings, moderations, media generation — the OpenAI-compatible inference surface | 580+ utility endpoints: Islamic tools, web scraping, anime, finance, crypto, QR codes, weather, security, and more |
| **Key prefix** | `auc_live_…` / `auc_premier_…` / `auc_platinum_…` / `auc_free_…` | `auc_rest_…` |
| **Base URL** | (same origin — this page's domain) | https://api.fallsad.biz.id/api |
| **Auth** | Bearer token in `Authorization` header | `?key=…` query param, `x-api-key` header, or Bearer |
| **Quota** | RPM + daily requests by plan (Free → Platinum) | 5 calls/day free (admin-adjustable per key) |
| **Key source** | Issued by AuCore after plan purchase, or Google sign-in (free) | Issued from the admin dashboard (API keys tab) |
| **Use it for** | Chatbots, RAG, agents, code generation, summarization, image/video generation | Utility microservices: prayer times, weather, currency, QR, short links, anime search… |
**Rule of thumb:** if you're calling a model (GPT, Claude, Gemini, Llama…), use the **AI API** with your `auc_live_` key. If you're calling a utility endpoint (weather, QR, prayer times…), use the **REST API Toolkit** with your `auc_rest_` key. They never mix — a `auc_rest_` key cannot call chat completions, and a `auc_live_` key cannot call toolkit features.
## 3. Authenticate
Send your key as a bearer token on every request.
```
Authorization: Bearer auc_live_a1b2c3d4e5f6g7h8
Content-Type: application/json
```
| Status | Meaning |
| --- |--- |
| `401` | Key missing or unknown |
| `403` | Key revoked or expired, or model above your plan |
| `429` | Rate or daily budget exceeded |
## 4. List models
```
curl /models \
-H "Authorization: Bearer $AUCORE_KEY"
```
```
{
"object": "list",
"data": [
{
"id": "aucore-router-auto",
"owned_by": "Anthropic",
"context_window": 1000000,
"modalities": ["text", "vision", "tools"],
"min_plan": "premier",
"available": true
}
]
}
```
`available` reflects your own plan, so you can filter the catalog client-side.
## 5. Chat completions
```
curl /chat/completions \
-H "Authorization: Bearer $AUCORE_KEY" \
-H "Content-Type: application/json" \
-d '{
"model": "aucore-router-auto",
"messages": [
{"role": "system", "content": "You are concise."},
{"role": "user", "content": "What is retrieval augmented generation?"}
],
"temperature": 0.7,
"max_tokens": 1024
}'
```
**Response**
```
{
"id": "chatcmpl_aucore_8f2a…",
"object": "chat.completion",
"model": "aucore-router-auto",
"choices": [{
"index": 0,
"message": {"role": "assistant", "content": "RAG is…"},
"finish_reason": "stop"
}],
"usage": {"prompt_tokens": 24, "completion_tokens": 148, "total_tokens": 172}
}
```
### Parameters
| Field | Type | Notes |
| --- |--- |--- |
| `model` | string | Required. Any ID from the catalog. |
| `messages` | array | Required. Roles: system, user, assistant. |
| `temperature` | number | 0–2. Default 1. |
| `max_tokens` | integer | Capped at 32,000. |
| `top_p` | number | Nucleus sampling. |
| `stream` | boolean | Server-sent events when true. |
| `tools` | array | Premier and Platinum only. |
## 6. Streaming
Set `"stream": true` and read server-sent events. Each chunk is a `data:` line, ending with `data: [DONE]`.
```
data: {"choices":[{"delta":{"content":"RAG"}}]}
data: {"choices":[{"delta":{"content":" combines"}}]}
data: [DONE]
```
```
// Node.js — stream with the OpenAI SDK
const stream = await client.chat.completions.create({
model: "aucore-router-auto",
messages: [{ role: "user", content: "Write a haiku" }],
stream: true,
});
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}
```
## 7. Automatic model selection
Send `aucore-router-auto` as the model and AuCore chooses the cheapest model capable of handling the prompt: short prompts go to a fast small model, code-heavy or long prompts escalate automatically.
```
{
"model": "aucore-router-auto",
"messages": [{"role": "user", "content": "Summarise this in one line: …"}]
}
```
## 8. Use an existing SDK
```
# Python
from openai import OpenAI
client = OpenAI(base_url=, api_key=os.environ["AUCORE_KEY"])
r = client.chat.completions.create(
model="aucore-router-auto",
messages=[{"role": "user", "content": "Hello"}],
)
print(r.choices[0].message.content)
```
LangChain, LlamaIndex, the AI SDK and anything else that accepts a custom base URL work the same way. `/v1` is accepted as an alias, so `…/api/v1` and `…/api` both resolve.
## 9. Token optimization
Every request passes through the AuCore token minimizer before it reaches a model provider. Whitespace is normalized, oversized histories are windowed to fit your plan's context budget, and bloated tool results are capped — typically saving 15–40% of input tokens on long conversations, which makes free-tier quotas last dramatically longer.
- Automatic by default; nothing to configure.
- Add `"optimize": "aggressive"` to the request body for deeper compression (strips filler phrases).
- Check the savings in every response: headers `X-AuCore-Tokens-In` / `X-AuCore-Tokens-Saved`, or the `aucore.tokens_minimized` field.
## 10. Rate limits
| Plan | Per minute | Per day | Context | Weight |
| --- |--- |--- |--- |--- |
| Basic | 20 | 1,500 | 64K | 1× |
| Premier | 60 | 6,000 | 200K | 3× |
| Platinum | 180 | 25,000 | 1M | 9× |
Every response includes limit headers:
```
X-AuCore-Plan: platinum
X-RateLimit-Limit: 180
X-RateLimit-Remaining: 174
X-RateLimit-Reset: 1786000060
X-RateLimit-Daily-Remaining: 24985
```
## 11. Errors
```
{
"error": {
"type": "rate_limit_exceeded",
"message": "Daily request budget reached for plan basic.",
"code": 429,
"retry_after": 41,
"reset_at": "2026-08-17T00:00:00.000Z"
}
}
```
Retry `429` and `502` with exponential backoff plus jitter. Never retry `400` or `403` without changing the request.
## 12. Account management & support
Beyond chat, the gateway exposes account endpoints for everything the dashboard does — all with the same Bearer key.
### Profile & usage
```
PATCH /account/profile # update your name / email
GET /account/history?days=30 # daily request series (max 90 days)
GET /account/requests?limit=50 # recent request log (metadata only)
```
### Secondary keys
Mint up to five named keys for separate projects. They authenticate as your account with the same plan limits and can be revoked independently — no need to share the master key.
```
POST /account/keys # { "name": "chatbot-prod" } → key shown once
GET /account/keys # list every secondary key
DELETE /account/keys/:id # revoke one key instantly
```
### Webhooks
Register up to three HTTPS endpoints and AuCore POSTs events to them: `usage.daily`, `quota.warn` (≥80% of the daily budget) and `key.rotate`.
```
POST /account/webhooks # { "url": "https://your.app/hook", "events": ["usage.daily"] }
GET /account/webhooks # list registered webhooks
DELETE /account/webhooks/:id
```
### Support & subscribe
```
POST /support # { name, email, topic, message, consent: true }
POST /subscribe # { email } → product updates by email
```
Support requests **require** `consent: true` (the checkbox on the [support form](https://ai.aunuhost.bond/support)) and a valid email — replies are sent there by our email plane. Subscribers receive feature updates and promos; unsubscribe by contacting support.
## 13. Good practice
- Keep keys on your server; have your own backend call AuCore.
- Rotate immediately if a key may have leaked — old keys stop working at once.
- Set `max_tokens` deliberately; it is the simplest cost control you have.
- Use `aucore-router-auto` when quality requirements vary per request.
- Log the `id` from responses so support can trace a specific call.
## 14. Official SDK
The AuCore SDK is a zero-dependency JavaScript client that works everywhere — Node.js 18+, browsers, Deno, Bun, and edge runtimes. No npm install needed — download it directly:
**Download the SDK**
Single file, ~8 KB, zero dependencies
[Download .mjs](https://ai.aunuhost.bond/assets/sdk/aucore-sdk.mjs)
### Quick start
```
// Node.js / Deno / Bun / edge — import the downloaded file
import AuCore from "./aucore-sdk.mjs";
const ai = new AuCore({ apiKey: "auc_live_…" });
// Chat completion
const res = await ai.chat.create({
model: "aucore-router-auto",
messages: [{ role: "user", content: "Hello!" }]
});
console.log(res.choices[0].message.content);
// Streaming
const stream = await ai.chat.create({ messages: […], stream: true });
for await (const chunk of stream) {
process.stdout.write(chunk.choices[0]?.delta?.content ?? "");
}
// REST toolkit (separate key)
const rest = new AuCore({ restKey: "auc_rest_…" });
const weather = await rest.rest.call("info/weather", { city: "Jakarta" });
```
### Browser usage (no build step)
In a browser, add a `type="module"` script tag that imports the SDK from this site's CDN at
`/assets/sdk/aucore-sdk.mjs`, then instantiate `new AuCore({ apiKey: "auc_live_…" })`
and call `ai.chat.create()` — the same API as the Node.js example above.
**How it works:** the SDK is a single ES module that wraps the same REST API you'd call with `fetch`. It adds automatic retry on 429/5xx, request timeouts, typed errors, and a clean API surface (`ai.chat.create()`, `ai.rest.call()`). Since it's zero-dependency, you can copy the file into any project — no package manager needed. If you prefer npm, run `npm publish` from the `sdk/` folder after setting up an npm account.
## 15. REST API Toolkit — quick reference
The toolkit is a separate plane with its own base URL and key. Full interactive catalog at [/restapi](https://ai.aunuhost.bond/restapi).
```
# call any toolkit feature with your auc_rest_ key
curl "https://api.fallsad.biz.id/api/islamic/prayer-times?lat=-6.2&lon=106.8&key=auc_rest_…"
curl "https://api.fallsad.biz.id/api/info/weather?city=Jakarta&key=auc_rest_…"
curl "https://api.fallsad.biz.id/api/tools/qr-code?text=hello&key=auc_rest_…"
```
Every response carries rate-limit headers (`X-RateLimit-Limit`, `-Remaining`, `-Reset`) so you can track your quota client-side. Check `GET /me` for a full usage report.
---
Need something not covered here? See the [full API reference](https://ai.aunuhost.bond/reference),
the [FAQ](https://ai.aunuhost.bond/faq), or [contact support](https://ai.aunuhost.bond/support).
---
# REST API Toolkit — AuCore
> 580+ REST API features: Islamic tools, web utilities, anime & manga discovery, information and developer tools — free API key, 5 calls/day.
Source: https://ai.aunuhost.bond/restapi
Search features
Category
Your API key (only needed to run features)
——
---
# Model Catalog — AuCore
> Every model available through AuCore, with context window, modality, minimum plan and one-click copy of the model ID.
Source: https://ai.aunuhost.bond/model
Search
Provider
Minimum plan
Capability
Sort
—
| Model | Provider | Context | Capabilities | Speed | Min plan | |
| --- |--- |--- |--- |--- |--- |--- |
No model matches those filters.
---
# Pricing — AuCore
> AuCore pricing: Basic Rp50,000, Premier Rp100,000, Platinum Rp200,000 per month. Higher plans get more throughput and priority dispatch.
Source: https://ai.aunuhost.bond/plan
Prices in IDR, billed monthly. Keys are issued after payment is confirmed.
Priority
## What "priority" actually means
Requests enter a weighted queue. Under normal load everyone is served
immediately. When capacity tightens, the queue drains in proportion to plan
weight — so Platinum keeps flowing while lower tiers wait briefly.
Each plan also has a guaranteed floor, so no tier is ever
starved completely.
### Dispatch share under full load
simulated
Comparison
## Feature matrix
| Capability | Basic | Premier | Platinum |
| --- |--- |--- |--- |
### Not sure which plan fits?
Enter your expected traffic in the usage calculator and we'll
show the
cheapest plan that covers it, with headroom warnings.
[Open calculator →](https://ai.aunuhost.bond/usage)
Questions
## Billing & plans
More answers in the [full FAQ](https://ai.aunuhost.bond/faq).
## Ready when you are
Tell us your plan and we'll issue your key.
Upgrades apply instantly, no key change needed.
[Request a key](https://ai.aunuhost.bond/support)[I have a key](https://ai.aunuhost.bond/login)
---
# API Reference — AuCore
> Complete AuCore API reference: every endpoint, parameter, header and error code.
Source: https://ai.aunuhost.bond/reference
Reference
# API reference
Every endpoint, with required headers and response shape. Base URL:
---
# Features — AuCore · 550+ API Features in One Cloud
> Explore every AuCore capability: AI inference, 550+ REST endpoints across 25 categories, media tools, finance data, security suite and more.
Source: https://ai.aunuhost.bond/features
v2.0.3 — 550+ endpoint · 25 kategori · satu gerbang
# Semuanya, di satu tempat
Sepuluh keluarga alat baru bergabung di v2.0.3.
[Lihat Katalog](https://ai.aunuhost.bond/restapi.html)[Harga](https://ai.aunuhost.bond/plan.html)
0+Fitur API
0Kategori
0%Ketersediaan
0/day*Panggilan
Gratis/Hari*
AI & Intelligence
## Analisis teks tingkat lanjut, tanpa GPU
Ringkasan ekstraktif, entropi, n-gram, deteksi plagiarisme, sentiment dwibahasa
(EN/ID) — semua dijalankan di edge.
🧠
### Text Intelligence
Summarizer frekuensi, Flesch readability, keyword density TF-IDF, Jaccard similarity,
shingle-based plagiarism hint.
ai/text-summarizeai/readability-scoreai/plagiarism-hint
🔎
### Entity Extraction
Tarik email, nomor telepon (+62 aware), tanggal multi-format, hashtag camelCase-split,
dan mention dari teks mentah apa pun.
ai/emails-extractai/phone-extractai/date-extract
🌍
### Language & Encoding
Deteksi script 8 aksara (Latin→Hangul), tebahan bahasa Nusantara, profil encoding UTF-8,
dan slug multibahasa.
ai/language-guessai/encoding-profileai/slug-multilang
Security Suite
## Kriptografi nyata di edge runtime
TOTP RFC-6238 asli via WebCrypto, JWT HS256 sign & verify, brute-force Caesar dengan
scoring bahasa Inggris, audit header keamanan.
🔐
### Auth Codes
Generate kode TOTP 6 digit live dengan sisa detik periode — cocok untuk testing 2FA tanpa
aplikasi authenticator.
security/totp-codesecurity/jwt-sign-hs256security/jwt-verify-hs256
🛡️
### Hardening Audit
Nilai header HSTS/CSP/XFO/referrer-policy, cek SPF & DMARC domain via DoH, dan skor
kekuatan password berbasis entropi.
security/header-auditwebtools/spf-recordutility/password-strength
🕵️
### Cipher Playground
ROT-N semua 25 rotasi sekaligus, Caesar brute-force terperingkat, hash comparator
bit-level dengan analisis avalanche.
security/rot-n-allsecurity/caesar-brutesecurity/hash-compare
Math · Time · Geo · Color
## Mesin komputasi presisi
BigInt factorial hingga 170!, cron next-runs scanner, haversine geodesi, WCAG contrast
auditor, dan palet harmonis otomatis.
📐
### Math Engine
Faktorisasi prima, kombinasi BigInt, statistik lengkap (mean/median/mode/σ), bitwise
visual binary, det matriks 2×2–3×3.
math/factorialmath/statisticsmath/matrix-det
⏱️
### Date & Time
Umur detail (detak jantung!), ISO week, hari kerja skip-weekend, countdown real-time,
umur di planet Merkurius–Neptunus.
datetime/age-detaildatetime/cron-next-runsdatetime/age-on-planet
🗺️
### Geo Studio
Geocode/reverse Nominatim, elevasi OpenTopoData, bounding box radius km, bearing kompas
16 arah, flag emoji per negara.
geo/geocodegeo/elevationgeo/bounding-box
🎨
### Color Lab
Shade/tint generator, mixer rasio, palet mood (vibrant/pastel), warna terdekat 40 nama
CSS, konversi kelvin→RGB fisik.
color/shadescolor/random-palettecolor/from-temperature
Weather · Poetry · Edu · Random
## Data hidup & kreasi harian
AQI ganda US/EU, marine surf report, 130 ribu puisi PoetryDB, sieve prima edukatif,
secret santa anti-self, bracket turnamen acak.
🌦️
### Weather Extra
Kualitas udara PM2.5/O₃/CO, UV index dengan saran proteksi, gelombang laut untuk surfer,
perbandingan cuaca multi-kota.
weather/air-qualityweather/uv-indexweather/marine-conditions
📜
### Poetry & Words
Puisi acak/by-author/by-title, rima Datamuse bersuku kata, sinonim+antonim satu
panggilan, adjective untuk copywriting.
poetry/randompoetry/rhymespoetry/synonyms-antonyms
🎓
### Education Tools
Tabel perkalian pola, pecahan → mixed number, sieve Eratosthenes visual, penjumlahan
biner schoolbook, klasifikasi sudut.
edu/prime-sieveedu/fraction-toolsedu/binary-add
🎲
### Random Generators
Undian lotere + odds, pembagi tim adil, short-ID bebas ambigu, koin berbobot
probabilitas, draw-from-hat tanpa pengembalian.
rng/lottery-numbersrng/team-splitterrng/secret-santa
## Siap membangun sesuatu yang hebat?
Ambil kunci REST gratis permanen dalam hitungan detik. Tanpa kartu kredit, tanpa
kedaluwarsa.
[Dapatkan Kunci API](https://ai.aunuhost.bond/restapi.html)[Dokumen](https://ai.aunuhost.bond/docs.html)
---
# FAQ — AuCore
> Answers to common questions about AuCore keys, plans, limits, privacy and troubleshooting.
Source: https://ai.aunuhost.bond/faq
No question matches. [Ask us directly](https://ai.aunuhost.bond/support).
---
# Support — AuCore
> Request an AuCore key, report an issue, or ask a billing question.
Source: https://ai.aunuhost.bond/support
### Send a request
### Response times
Basic**Best effort**
Premier**24 hours**
Platinum**4 hours**
### Try these first
[Check current system status →](https://ai.aunuhost.bond/status)[Browse the FAQ →](https://ai.aunuhost.bond/faq)[Error code reference →](https://ai.aunuhost.bond/docs#errors)[Key security guide →](https://ai.aunuhost.bond/keys)
### Before you write
· Never paste a full API key. The last four characters are enough.
· Include the `id` from a failing response if you have one.
· For security reports, use the Security report topic.
### Get AuCore updates
New features, model drops and promos — a few emails a month, no spam. Unsubscribe any time.
---
# Security — AuCore
> How AuCore protects keys, credentials and prompt content, plus how to report a vulnerability.
Source: https://ai.aunuhost.bond/security
Trust
# Security overview
What we do to keep your credentials and content safe, stated plainly.
### Prompts are not stored
Message bodies pass through in memory only. We record model, token counts, latency and status — never content.
### Keys are hashed
API keys are stored as salted hashes. We cannot read your key back, which is why rotation exists.
### Credentials encrypted
Prompt and completion bodies are never persisted — only usage metadata is recorded.
### Everything audited
Every administrative action is written to an append-only audit log with actor, target and timestamp.
## Transport
- TLS on every endpoint. There is no plaintext HTTP entry point.
- HSTS with preload on all web properties.
- Strict security headers: no sniffing, framing restricted, referrer trimmed.
## Access control
- Customer keys are scoped to a single account and cannot read anyone else's data.
- Administrative access is guarded by a single secret compared in constant time.
- Inference providers are reached only from the server side; their credentials never reach a browser.
- Failed authentication attempts are rate limited.
## Isolation and quota
Quota counters are strongly consistent per account, so one customer's traffic can never
consume another's budget. Capacity has guaranteed floors per plan, so a large tenant
cannot starve smaller ones completely.
## Data retention
| Data | Retention |
| --- |--- |
| Prompt and output bodies | Not stored |
| Request metadata | 7 / 30 / 90 days by plan |
| Security and audit logs | 90 days |
| Account record | Account life plus 30 days |
## Reporting a vulnerability
If you believe you have found a security issue, contact us through the
[support page](https://ai.aunuhost.bond/support) with the subject **Security report**. Please include:
- A description of the issue and its impact.
- Steps to reproduce, ideally minimal.
- Whether any real customer data was accessed.
We acknowledge reports within 3 business days and will keep you updated until resolution.
Please do not run automated scanners or load tests against production without written permission,
and do not access data that is not yours.
## Your responsibilities
- Keep keys server-side and rotate them if exposure is suspected.
- Add authentication to any route of yours that forwards to AuCore.
- Set `max_tokens` to bound cost and output size.
See the [key security guide](https://ai.aunuhost.bond/keys) for a practical checklist,
and our [Privacy Policy](https://ai.aunuhost.bond/privacy) for data handling detail.
---
# About — AuCore
> AuCore is built by AuR AI to make frontier models simple to adopt for teams in Indonesia and beyond.
Source: https://ai.aunuhost.bond/about
### The problem
Every provider has its own SDK, billing portal, quota model and failure behaviour.
Supporting four of them means four integrations and four invoices.
### Our approach
One endpoint, one key, one bill. We keep the OpenAI request format because it is
already the common language of the ecosystem.
### What we refuse
We do not store your prompts, do not train on your data, and do not
run advertising trackers on this site.
Principles
## How we make decisions
## Work with us
Questions about the platform, a custom allocation, or a partnership?
We reply to every message.
[Get in touch](https://ai.aunuhost.bond/support)[See what we shipped](https://ai.aunuhost.bond/changelog)
---
# Integrations — AuCore
> Copy-paste setup for OpenAI SDK, LangChain, LlamaIndex, AI SDK, Cursor, Continue and more.
Source: https://ai.aunuhost.bond/integrations
---
# Usage Calculator — AuCore
> Estimate which AuCore plan fits your traffic, with headroom warnings and cost per request.
Source: https://ai.aunuhost.bond/usage
### Your workload
Requests per day
Peak requests per minute
Avg input tokens
Avg output tokens
Largest context needed
I need tool / function calling
### Recommendation
—
### Plan by plan
| Plan | Price | Daily headroom | Burst headroom | Context | Verdict |
| --- |--- |--- |--- |--- |--- |
### Monthly totals
---
# Token Counter — AuCore
> Estimate token count and request cost before you send it, for any AuCore model.
Source: https://ai.aunuhost.bond/tokens
Your text
### Against a model
Model
Expected output tokens
---
### Budget impact
Plan
Requests like this per day
---
Estimates use roughly 4 characters per token, the common average for
English. Real counts vary by model and language — treat this as a planning tool, and read
`usage` in the API response for exact numbers.
---
# Compare Models — AuCore
> Compare AuCore models side by side on context window, capabilities, speed and required plan.
Source: https://ai.aunuhost.bond/compare
Select models (up to 4)
Select at least one model above.
---
# Terms of Service — AuCore
> AuCore Terms of Service — plans, acceptable use, liability.
Source: https://ai.aunuhost.bond/terms
Legal
# Terms of Service
Last updated 25 August 2026 · Operated by AuR AI (“AuCore”, “we”, “us”).
In short: you get a personal key tied to a paid plan, you must not abuse or resell it, model output comes from third-party providers and may be wrong, and we may suspend keys that break these rules. This summary does not replace the full terms below.
## 1. Agreement
These Terms of Service govern your access to the AuCore website, dashboards and API (the “Service”), operated by AuR AI. By redeeming an access key or calling any endpoint, you accept these terms. If you do not agree, do not use the Service.
## 2. Accounts, keys and webhooks
- Keys are issued by an AuCore administrator once a plan is selected and paid for.
- A key identifies one account. You are responsible for all activity under your key, including usage by your own end users.
- Keep keys server-side. Do not embed them in mobile apps, browser bundles, public repositories or screenshots.
- You may rotate your key at any time from your dashboard. Rotation invalidates the previous key immediately.
- You may issue up to five named **secondary keys** for separate projects. Secondary keys authenticate as your account, share its plan limits, and may be revoked independently; you remain responsible for their use.
- You may register up to three **webhook URLs**. We deliver event notices (usage summaries, quota warnings, key rotations) to the endpoints you register; you must keep them under your control and protect any data received there.
- We may revoke any key without notice if we detect compromise, fraud, non-payment or abuse.
## 3. Plans, priority and payment
- Plans are Basic (Rp50,000 / month), Premier (Rp100,000 / month) and Platinum (Rp200,000 / month).
- Higher plans receive greater throughput, larger context ceilings and a higher dispatch weight. Priority is relative and is not a guaranteed latency figure.
- Plans are prepaid. Fees are non-refundable once a key has been issued and used, except where required by law.
- Daily request budgets reset at 00:00 UTC and do not roll over.
- Upgrades take effect immediately. Downgrades apply at the next renewal unless agreed otherwise.
- We may change prices or limits with at least 14 days notice. Prepaid periods already purchased are unaffected.
## 4. Acceptable use
You must not use the Service to:
- generate or distribute content that is unlawful, defamatory, sexually exploitative of minors, or that incites violence or self-harm;
- create malware, phishing material or spam;
- infringe intellectual property, privacy or publicity rights;
- attempt to extract model weights, reverse-engineer routing internals, or bypass authentication, quota or safety controls;
- resell raw API access, share your key with third parties, or operate a competing reselling service without a written agreement;
- run load or penetration tests without prior written permission;
- submit personal data of others without a lawful basis, or regulated data (payment card, health records) without a separate agreement.
You must also comply with the acceptable-use policies of the model providers your requests reach.
## 5. Model routing
- Requests are routed across our inference layer automatically. Model availability may change as we add or retire models.
- We select providers to keep responses fast and reliable; individual model IDs are stable aliases that may be served by more than one upstream.
- If every inference route for your request is unavailable, the request fails with an explicit error rather than degrading silently.
## 6. Third-party model output
Requests are fulfilled by third-party model providers. Their availability, output quality and content policies are outside our control. Output may be inaccurate, biased or offensive. You must review output before relying on it, and must not present it as professional legal, medical or financial advice.
## 7. Your content
You retain all rights in the prompts you send and, as between you and us, in the output you receive. You grant us a limited right to process your content to operate the Service, enforce these terms and produce aggregate statistics. We do not use your prompts to train models.
## 8. Availability, support and consent
The Service is provided on a best-effort basis. Published availability figures are historical and are not a contractual SLA unless your plan states otherwise. Support targets are: Basic — community; Premier — 24 hours by email; Platinum — 4 hours priority. Planned maintenance and material platform events are announced on the status page and through in-product announcements where practical.
When you submit a support request you must explicitly accept these Terms and our Privacy Policy via the consent checkbox on the support form. Submitting the form with the box ticked constitutes your signed consent for us to process the request and the contact details in it, solely to respond to you. Requests submitted without consent are rejected by the platform.
## 9. Suspension and termination
We may suspend or terminate access immediately for breach of these terms, non-payment, legal obligation, or risk to platform integrity. You may stop using the Service at any time. On request we delete your key and profile within 30 days, subject to legal retention duties.
## 10. Disclaimers and liability
The Service is provided “as is” and “as available”, without warranties of any kind, express or implied, including merchantability, fitness for a particular purpose and non-infringement. To the maximum extent permitted by law, our aggregate liability arising out of or relating to the Service is limited to the fees you paid in the three months preceding the event giving rise to the claim. We are not liable for indirect, incidental, special, consequential or punitive damages, nor for lost profits, data or goodwill.
## 11. Indemnity
You will indemnify and hold harmless AuR AI and its personnel against claims, damages and reasonable costs arising from your use of the Service in breach of these terms or applicable law.
## 12. Changes
We may update these terms. Material changes are announced on this page and, where we hold your email address, by email at least 14 days before they take effect. Continued use after the effective date constitutes acceptance.
## 13. Governing law
These terms are governed by the laws of the Republic of Indonesia. Disputes will be resolved in the competent courts of Indonesia, without prejudice to mandatory consumer protections in your jurisdiction.
---
Questions? Reach us on the [support page](https://ai.aunuhost.bond/support). See also our
[Privacy Policy](https://ai.aunuhost.bond/privacy) and [security overview](https://ai.aunuhost.bond/security).
---
# Privacy Policy — AuCore
> AuCore Privacy Policy — what we collect, how prompts are handled, and your rights.
Source: https://ai.aunuhost.bond/privacy
Legal
# Privacy Policy
Last updated 25 August 2026 · Operated by AuR AI (“AuCore”, “we”, “us”).
In short: we store the minimum needed to run a metered API — your account record, a hash of your key, and request metadata. Prompt and output bodies are not stored. We never sell your data and never train models on your content.
## 1. Who we are
AuCore is operated by AuR AI, the data controller for the account and usage data described below. For content you send through the API, you are the controller and we act as your processor.
## 2. What we collect
| Category | Examples | Purpose | Retention |
| --- |--- |--- |--- |
| **Account** | Name, email, plan, status, expiry | Issue and manage your key | Account life + 30 days |
| **Credentials** | Hashed API key, encrypted provider credentials | Authenticate requests | Until rotated or deleted |
| **Request metadata** | Timestamp, model, endpoint, token counts, latency, status | Quota, analytics, abuse detection | 7 / 30 / 90 days by plan |
| **Prompt & output** | Message content | Relayed for inference only | Not stored by AuCore |
| **Security logs** | Failed auth, rate-limit hits, admin actions | Protect the platform | 90 days |
| **Support requests** | Name, email, plan, message text | Answer your request — only after you tick the consent box | 120 days |
| **Secondary keys & webhooks** | Named key hashes, your webhook URLs | Multi-key access, event delivery | Until you remove them |
We do not use advertising cookies or third-party trackers. Your browser stores your key and cached profile locally so the dashboard works; clearing site data removes them.
## 3. Prompt content
Prompts and completions pass through the Service in memory and are forwarded to the selected model provider. We do not write message bodies to storage. Only metadata such as token counts, model, latency and status is recorded.
## 4. Legal bases
- **Contract** — issuing keys, metering usage, providing dashboards.
- **Legitimate interests** — security, abuse prevention, capacity planning, aggregate analytics.
- **Legal obligation** — tax, accounting and lawful requests.
- **Consent** — support requests (you tick the consent box on the form; the platform rejects requests without it), optional communications, withdrawable at any time.
## 5. Sharing
- **Cloud infrastructure providers** — edge hosting, compute and storage used to run the Service.
- **Model providers** (for example OpenAI, Anthropic, Google, Meta) process prompt content to generate output. Requests may be routed to whichever independent inference route currently serves your chosen model.
- **Email delivery provider** — support tickets are relayed to our support inbox through a transactional email service; the ticket content and your reply-to address are processed solely to answer your request.
- **Your webhook endpoints** — when you register webhooks, event payloads are delivered to URLs you control. You are the controller of any data your endpoints receive.
We do not sell personal data and do not share it for cross-context behavioural advertising. Disclosure to authorities occurs only where legally required, and we resist overbroad demands where lawful.
## 6. International transfers
Because the Service runs on a global edge network, data may be processed outside Indonesia, including in the United States and the European Union. Transfers rely on the safeguards offered by our providers, including standard contractual clauses where applicable.
## 7. Security
- TLS everywhere; no plaintext endpoints.
- API keys are stored as salted hashes, never in plain text.
- Prompt and completion bodies are never persisted — only usage metadata is kept.
- Administrative access is restricted and every privileged action is written to an audit log.
- Rate limiting on authentication attempts and least-privilege access to data stores.
No system is perfectly secure. If we discover a breach affecting your data, we will notify affected accounts and, where required, regulators without undue delay.
## 8. Your rights
Subject to applicable law you may request access, correction, deletion, export, restriction of processing, or object to processing based on legitimate interests. Contact us via the support page; we respond within 30 days and may ask you to verify control of your key or registered email. You may also lodge a complaint with your local data protection authority.
## 9. Children
The Service is not directed to children under 13, or the higher local minimum age. We do not knowingly collect their data; contact us for removal if you believe we have.
## 10. Changes
Material changes are announced on this page and by email where we hold your address, at least 14 days before taking effect. The “last updated” date above reflects the current version.
---
Questions? Reach us on the [support page](https://ai.aunuhost.bond/support). See also our
[Terms of Service](https://ai.aunuhost.bond/terms) and [security overview](https://ai.aunuhost.bond/security).