AIGet is our OpenAI-compatible AI gateway: one key, one prepaid balance, and automatic failover across the models you already use. Managed Docker hosting is next — still in development.
Endpoint
Routing
The Seneco ecosystem
AIGet is available today. SentinelX Cloud is still being built — there is no beta, no launch date and no pricing to announce yet.
One API for chat, tool calling, images, PDFs and audio across the major model providers. OpenAI-compatible, with routing and failover handled for you.
Managed Docker hosting is in development. It is not available yet, and we are not accepting workloads or publishing pricing.
How AIGet works
One request goes in. AIGet checks the key and balance, picks a model that fits your policy, and fails over to another provider if one is unavailable.
AIGet
One integration, the whole model ecosystem. Keep your existing OpenAI-compatible code and let the gateway handle routing, failover and metering.
Chat, tool calling, images, PDFs and audio through the same API and the same request shape.
Pin a model or let aiget/auto choose by cost, quality, latency or a balanced policy. Retries move to another provider when one fails.
A USD balance charged per token actually used. No monthly subscription, no unused credits expiring.
Prompts are not stored for training. You choose which providers may receive your data, and spending caps can be set per key and project.
curl https://api.aiget.tech/v1/chat/completions \ -H "Authorization: Bearer $AIGET_KEY" \ -H "Content-Type: application/json" \ -d '{ "model": "aiget/auto", "messages": [{ "role": "user", "content": "Summarise this report" }], "stream": true }'$5
Free credit for new accounts
$0
Monthly subscription
60/min
Default rate limit per key
Developer experience
AIGet follows OpenAI request and response shapes, so the SDK, framework or agent you already use can connect by changing the base URL and key.
The same Chat Completions request and response shape. Point your client at api.aiget.tech/v1 and use an AIGet key.
One base URLSet stream: true and chunks are forwarded as the provider sends them, with routing headers available before the first byte.
SSETool calling and image input use the usual OpenAI tools, tool_choice and image_url fields. Unsupported models are filtered out first.
Tools · imagesReasoning models can think before answering. Override the default with chat_template_kwargs when you need to.
chat_template_kwargsRequests are limited per API key at 60 per minute by default, and spending caps can be set per key and per project.
60 req/min defaultEvery change to your balance records the reason, the resulting balance and the request or payment behind it.
DashboardSentinelX Cloud Soon
We are building a way to run containerised services without operating a cluster. It is not available yet — there is no public beta and no open signup.
The product is being built. We have not published a launch date, feature list or price.
Please do not migrate production services to SentinelX Cloud yet. There is no SLA or support commitment for it today.
When there is something concrete to share, it will be published here. You can register interest through the contact form.
NoticeSentinelX Cloud is in development. No availability, regions or pricing has been announced.
Keys & data
These are controls AIGet documents today. The full detail, including payment verification and organisation isolation, lives on the AIGet security page.
API keys are stored in a form that cannot be reversed and shown only once at creation.
Provider credentials are encrypted, with the decryption key kept separately from the data.
A key can only reach the project it was created for. Usage, balance and models stay isolated.
AIGet's stated policy is that prompts are not stored or used for training, and you choose which providers receive data.
Each balance change records the reason, the resulting balance and the request or payment behind it.
Administrative tools are not reachable from the public API and require a secret token plus a permitted origin.
Questions
For the complete reference, error codes, limits and model pricing, use the AIGet documentation and support pages.
AIGet is an API gateway that puts many AI models behind one OpenAI-compatible endpoint. It handles routing, provider failover, usage tracking and token-based billing from a single prepaid USD balance.
Yes. Request and response shapes follow OpenAI Chat Completions. In most projects you only change the base URL to https://api.aiget.tech/v1 and use your AIGet API key.
Send a model id to pin a specific model, or send aiget/auto to let the router choose. You can steer routing per request with the X-AIGet-Policy header: cost, quality, latency or balanced. The response reports the model and provider that answered.
AIGet's published policy is that prompts are not stored or used for training, and you choose which providers may receive your data. Usage and charges remain traceable in the dashboard. The full policy is available on aiget.tech.
The balance is prepaid in USD and charged per token actually used. Credits never expire and there is no monthly subscription. Top-ups are paid in IDR through Midtrans, with the exchange rate shown before payment.
No. Managed Docker hosting is in development. There is no public beta, no open signup and no published launch date or pricing. You can register interest through the contact form.
Integration
Install the OpenAI SDK, point it at AIGet, and keep the rest of your code. Model choice, retries and metering happen at the gateway.
import OpenAI from "openai"; const client = new OpenAI({ baseURL: "https://api.aiget.tech/v1", apiKey: process.env.AIGET_KEY,}); const reply = await client.chat.completions.create({ model: "aiget/auto", messages: [{ role: "user", content: "Summarise this report" }],});AIGet · live
Create an AIGet account, verify your email, enable 2FA and create an API key. The credit is added automatically — no credit card required.
AIGet is live today. SentinelX Cloud is still in development.