Moving EidosStack AI Gateway Into Meldport

khaerul anwar — Sun, 01 Nov 2026 17:07:28 +0000

I retired EidosStack AI Gateway as a standalone product and moved its API work into Meldport.

Meldport brings model discovery and API access together. Its public catalog lets you compare published model IDs, context windows, capabilities, and token rates before choosing a route. A project key and balance cover the published catalog.

For language models, the gateway accepts the familiar Chat Completions request shape. Point an OpenAI-compatible client at https://api.meldport.com/v1, choose a published model ID, and send a request:

curl https://api.meldport.com/v1/chat/completions \
  -H "Authorization: Bearer $MELDPORT_API_KEY" \
  -H "Content-Type: application/json" \
  -H "Idempotency-Key: request-123" \
  -d '{
    "model": "YOUR_MODEL_ID",
    "messages": [{"role": "user", "content": "Hello"}]
  }'

The API key stays on your server. The docs cover key scope, request limits, retries, and billing.

Image, video, and audio generation use their own workflows. They can involve input uploads, asynchronous jobs, and result retrieval, so they need more than a chat completion endpoint.

Meldport is available to the public now with prepaid, usage-based pricing. The official launch is set for 13 November 2026.

If you try it, I would appreciate feedback on the quickstart, the model details you need to compare routes, and how media generation fits into your app.

I built an AI gateway because I was tired of guessing what a request would cost

khaerul anwar — Sat, 29 Aug 2026 22:43:17 +0000

Every provider has a different pricing page.

If you use one provider, that is fine. But the moment you want to compare models across providers (and you should, because prices for the same task vary wildly), you end up with a spreadsheet, a bunch of open tabs, and the nagging feeling that the numbers went stale last week.

That was me for months. So I built the thing I actually wanted: EidosStack AI Gateway.

What it does

It is an OpenAI-compatible API gateway. One endpoint, one API key, 48+ models behind it from DeepSeek, Anthropic (Claude), OpenAI (GPT), Google (Gemini), Alibaba (Qwen), Moonshot (Kimi), and Zhipu (GLM).

The part I am most happy with is the pricing table. It shows input, output, and cache token prices per model, and it refreshes every 30 seconds. You see what a request will cost before you send it, not after the invoice arrives.

How billing works

Pay-as-you-go, no subscription. You create an API key, set a spending limit on it if you want, and top up when needed. Billing is in IDR with USD shown as a reference.

Prices on the gateway run up to 50% below the official provider rates. That is not a promo, it is just how we price.

What I learned building it

Keeping a pricing table honest is harder than it sounds. Providers change prices quietly, so the table has to be re-verified constantly instead of hand-edited once.
"OpenAI-compatible" is easy to claim and hard to get right. Tool calling and streaming were the parts that needed the most attention.
Per-key spending limits matter more to small teams than fancy routing. Nobody wants to discover a runaway loop ate their balance overnight.

Try it

The gateway is live at eidosstack.com/en/ai-gateway. The pricing table is public, so you can compare costs before signing up.

We are also launching on Product Hunt on September 8 if you want to follow along.