OpenAI-compatible · QRIS top-upSee pricing

DeepSeek models, paid in Rupiah.

One endpoint that works with the OpenAI SDKs you already use. Top up with QRIS, pay per token, keep your code.

Model
deepseek-flash
cache hit
$0.010
cache miss
$0.400
output
$1.600
from openai import OpenAI client = OpenAI(    base_url="https://api.larasrouter.com/v1",    api_key="lr_live_••••••••",) resp = client.chat.completions.create(    model="deepseek-flash",    messages=[{"role": "user", "content": "Halo!"}],)print(resp.choices[0].message.content)
Only the base URL and key change. Everything else stays.

Example request

deepseek-flash
cache hit · 8,000
$0.000080
cache miss · 4,400
$0.001760
output · 1,800
$0.002880

Charged to your balance

$0.004720

Metered per token and shown per request, to $0.000001.

01 — How it works

From Rupiah to first token in three steps.

No card, no subscription, no sales call. Scan, copy a key, ship.

  1. Step 1

    Top up with QRIS

    Scan with any Indonesian bank or e-wallet app. Add $1 to $100 of USD balance, paid in Rupiah.

  2. Step 2

    Create an API key

    One click in the console. Each key gets its own limits and an optional monthly budget.

  3. Step 3

    Call the endpoint

    Point your OpenAI client at our base URL and send chat completions exactly as you do today.

02 — Console

Every cent accounted for, to the sixth decimal.

Live balance, per-key monthly budgets, and per-request cost down to $0.000001.

Workspace
  • Overview
  • API keys
  • Usage
  • Billing

Overview

Sample data

Balance

$24.18

Top up with QRIS

Spend · this month

$5.82

39% of $15.00 budget

Requests · 14 days

KeyPrefixBudgetLast request
productionlr_live_7f3a…$10.00$0.004720
claude-codelr_live_c21d…$5.00$0.017728
staginglr_live_09be…No budget$0.002401

03 — Pricing

Pay per token. Nothing else.

USD per 1M tokens. Credits never expire. No minimums beyond your first $1 top-up.

Select a model to see what one request costsFull pricing and calculator

One request on

deepseek-flash
8,000 cache hit
$0.000080
4,400 cache miss
$0.001760
1,800 output
$0.002880

Total for one request $0.004720

The same request on each model

DeepSeek-V4.1-Flash$0.004720
DeepSeek-V4-Pro$0.017728
GLM-5.3-Flash$0.002401

04 — Why Laras Router

Built for developers who'd rather not need a foreign card.

  • Pay with QRIS

    Any bank app or e-wallet in Indonesia. Rupiah in, USD balance out.

  • No subscription

    Nothing renews. You spend only what you top up.

  • Credits never expire

    Your USD balance stays put until you use it, however long that takes.

  • OpenAI SDK compatible

    Change the base URL and key. Your existing code keeps working.

  • Per-token metering

    Cache hits, misses and output billed separately, visible per request.

  • Prompts aren't stored

    Requests pass through our gateway in memory and are not kept afterwards. The model's provider processes them under its own terms.

05 — Good to know

The fine print, up front.

More billing questions

No. Your first request needs a top-up, from as little as $1. In exchange there is no subscription, and unused balance never expires.

Send your first request today.

Top up from $1. No subscription, no expiry.

Questions? Our Indonesian support team is at support@larasrouter.com.