OpenAI-compatible · Preview coming

Drop-in AI for Cursor & VS Code.

Same API shape as OpenAI. Change the base URL. Pay less — because the network subsidises real compute, not random mining.

01How it works

Your editor.
Our cheaper backend.

1

Get an API key from Abakos (preview soon)

2

Set base URL to https://api.abakos.ai/v1

3

Pick a coder model — streaming works out of the box

Works with

Cursor · VS Code + Continue · Cline · Roo Code · Python openai · Node · LangChain · LiteLLM

No custom SDK. If it speaks OpenAI, it speaks Abakos.

02Setup

Copy. Paste. Code.

Use these configs once API keys are live. Join the waitlist to get early access and free credits.

Cursor

Settings → Models → Override OpenAI Base URL

Base URL: https://api.abakos.ai/v1
API Key:  abk_live_…  (from your Abakos dashboard)
Model:    abakos/qwen2.5-coder-32b-instruct

VS Code — Continue

~/.continue/config.json

{
  "models": [{
    "title": "Abakos Coder",
    "provider": "openai",
    "model": "abakos/qwen2.5-coder-32b-instruct",
    "apiBase": "https://api.abakos.ai/v1",
    "apiKey": "abk_live_…"
  }]
}

Python

from openai import OpenAI

client = OpenAI(
    base_url="https://api.abakos.ai/v1",
    api_key="abk_live_…",
)
client.chat.completions.create(
    model="abakos/qwen2.5-coder-32b-instruct",
    messages=[{"role": "user", "content": "Refactor this function…"}],
    stream=True,
)
03Models

Strong open models.
Lower price.

Open weights only (Llama, Qwen, DeepSeek, Mistral, Gemma) — the models you can actually run anywhere. Closed frontier models stay on their makers' APIs.

ModelBest forStatus
abakos/qwen2.5-coder-32b-instructIDE chat & agentsLaunch model
abakos/deepseek-coder-v2-liteTab autocompleteLaunch model
abakos/llama-3.3-70b-instructGeneral tasksPhase 2
abakos/nomic-embed-textEmbeddings / RAGPhase 2

Get on the developer waitlist.

Early API keys, free credits, and launch pricing. We'll email you when the preview is ready.

FAQ
Is the API live yet?

Preview is in development. Join the waitlist — we're onboarding developers in batches before public launch.

How is this cheaper than OpenRouter?

Miners earn network rewards on the same GPU cycles that serve your request — a real subsidy tied to paid work, not speculation. That lets us price below aggregators that only resell cloud GPUs.

Do I need crypto?

No. Pay with a card or prepaid balance. ABK token is optional for a discount later.

What about latency?

IDE use needs streaming under ~800ms first token. The preview routes to optimised partner GPUs; the decentralised network scales as supply grows.