Route requests through one OpenAI-compatible endpoint. Track usage, control credits, manage limits, and keep your AI costs predictable.
from openai import OpenAI client = OpenAI( base_url="https://ai.ixdm.co.id/v1", api_key="sk-ixdm-xxxxxxxx" ) response = client.chat.completions.create( model="deepseek-chat", messages=[ {"role": "user", "content": "Hello!"} ] ) print(response.choices[0].message.content)
Real-time usage from production AI workloads routed through the platform.
One endpoint, production-grade routing. The router handles the hard parts so your integration stays simple.
Route each model to the best upstream provider. Switch or add providers without touching your code.
Full SSE streaming support, fully OpenAI-compatible. Token-by-token responses with zero extra setup.
Failed upstreams are retried and temporarily cooled down, so transient provider errors stay invisible to your app.
Track tokens, requests, and per-key activity in real time from the dashboard, with full request logs.
Assign credit aliases per user, meter usage against a balance, and keep AI costs predictable per account.
Issue scoped API keys with their own request rates. Revoke or regenerate any key instantly.
From signup to AI-powered development in just a few minutes.
Create an account, generate an API key from the dashboard, and start using the service in seconds.
Paste the Base URL and API key into the tool you already use.
https://ai.ixdm.co.id/v1
Use your favorite models through one endpoint. Switch providers without changing integration.
Call the latest models from every major provider through a single OpenAI-compatible API.
Drop the router into the AI coding tools you already run every day.
Usage is metered against a credit balance with transparent per-model pricing. No subscriptions, no surprises.
Your account carries a credit balance. New accounts start with a free model alias assigned automatically.
Each model is a credit alias with its own input and output rate. You only pay for the models you actually call.
Every request deducts credits based on the tokens used. Watch your balance and history in real time.
Yes. The router exposes OpenAI-compatible /v1/chat/completions endpoint, so most SDKs work by changing only the base URL and key.
Use model aliases such as "deepseek-chat", "gpt-4o", or "claude-sonnet-4". See /docs#models for the full list.
Each account has a credit balance. Models are sold as credit aliases — you must be assigned an alias to use its slug. Each request deducts credits based on per-model pricing. See /docs#credits for details.
Each API key has a per-minute request rate. User accounts also use a credit balance for model access and usage. See /docs#limits for details.
Issue API keys from the dashboard. Monitor consumption and review request logs in real time.
Sign up free, grab an API key, and point your favorite tool at one endpoint.