API live · OpenAI-compatible

AI inference,
right at the edge.

Self-hosted OpenAI-compatible API. Drop-in replacement for OpenAI's client with predictable cost and zero vendor lock-in.

Read the docs → View models
Available models

Pick your model.

32 models across 9 providers. All share a unified OpenAI-compatible interface — switch with a single parameter.

Anthropic 12 models
Claude Sonnet 5
claude-sonnet-5
New
Claude Sonnet 4.6
claude-sonnet-4-6
Claude Sonnet 4.5
claude-sonnet-4-5
Claude Sonnet 4
claude-sonnet-4
Claude Opus 5
claude-opus-5
Max
Claude Opus 4.8
claude-opus-4-8
Claude Opus 4.7
claude-opus-4-7
Claude Opus 4.6
claude-opus-4-6
Claude Opus 4.5
claude-opus-4-5
Claude Opus 4.1
claude-opus-4-1
Claude Haiku 4.5
claude-haiku-4-5
Fast
Claude Fable 5
claude-fable-5
OpenAI 20 models
GPT 5
gpt-5
New
GPT 5 Codex
gpt-5-codex
GPT 5 Nano
gpt-5-nano
Fast
GPT 5.1
gpt-5.1
GPT 5.1 Codex
gpt-5.1-codex
GPT 5.1 Codex Max
gpt-5.1-codex-max
GPT 5.1 Codex Mini
gpt-5.1-codex-mini
GPT 5.2
gpt-5.2
GPT 5.2 Codex
gpt-5.2-codex
GPT 5.3 Codex
gpt-5.3-codex
GPT 5.3 Codex Spark
gpt-5.3-codex-spark
GPT 5.4
gpt-5.4
GPT 5.4 Mini
gpt-5.4-mini
GPT 5.4 Nano
gpt-5.4-nano
GPT 5.4 Pro
gpt-5.4-pro
GPT 5.5
gpt-5.5
GPT 5.5 Pro
gpt-5.5-pro
GPT 5.6 Luna
gpt-5.6-luna
GPT 5.6 Sol
gpt-5.6-sol
GPT 5.6 Terra
gpt-5.6-terra
The API

One endpoint. Standard format.

Use the official OpenAI SDK. Swap the base URL — nothing else changes.

chat.py
POST /v1/chat/completions 
# pip install openai
from openai import OpenAI

# Point the SDK at our endpoint. Same schema as OpenAI.
client = OpenAI(
    base_url="https://ai.semestaberjaya.my.id/v1",
    api_key="<your-key>",
)

response = client.chat.completions.create(
    model="claude-sonnet-5",
    messages=[
        {"role": "user", "content": "Halo, siapa kamu?"}
    ],
    stream=True,
)

for chunk in response:
    print(chunk.choices[0].delta.content or "", end="")
Why host it yourself

Boring infrastructure. Smart defaults.

Low latency
Edge-deployed on Indonesian infrastructure. Sub-second first-token time for local clients.
Private by default
Requests never leave our VPS. No telemetry, no third-party logging, no model training on your data.
OpenAI-compatible
Works with any client that supports the OpenAI Chat Completions spec. No SDK lock-in, no vendor migration cost.
Predictable cost
Flat monthly access. No per-token surprise bills, no rate-limit puzzles. Generous defaults.
Function calling
Built-in tool use for agent workflows. Hermes Agent, IDE integrations, automation pipelines.
Streaming + JSON
Server-sent events for UI responsiveness, structured JSON mode for deterministic pipelines.

Ready to integrate?

Request an API key and start making requests in minutes.

Request API access →