T0 LOCAL Reward enforcement works in the local simnet. Public GPU testnet is in development. View delivery status →
Product · In development
IN DEVELOPMENT

One base URL. Visible compute.

The planned API keeps familiar OpenAI request shapes while exposing the job and settlement behind each completion.

Designed for existing tools.

from openai import OpenAI

client = OpenAI(
  base_url="https://api.abakos.ai/v1",
  api_key="abk_..."
)

response = client.embeddings.create(
  model="qwen-embed",
  input=batch
)

Preview only. API keys and models are not issued yet.

01

Request

Use an OpenAI-compatible endpoint.

02

Job

The gateway creates a funded marketplace job.

03

Compute

A provider processes and proves the work.

04

Trace

The response includes a job reference visible in the explorer.

Honest availability.

T3 PLANNED

Embeddings

The first API workload after marketplace settlement works.

T3 PLANNED

Batch completions

Open-model completions with asynchronous job tracking.

T4 PLANNED

Streaming chat

Real-time and hybrid paths only after they are clearly labeled.

Get the right update.

Choose your path through the page you are on. We send product and testnet updates—not token-price promotion.

By joining, you agree to the privacy notice. Unsubscribe any time.