DOC · MICRODC-INFRA-001 v3.4
DOC · MICRODC-INFRA-001 · REV 04 · 2026.05

Distributed inference,
at the scale your
workloads demand.

Run document processing, data enrichment, and other batch AI workloads through an OpenAI-compatible API. Work queues to GPUs that would otherwise sit idle, so you pay for completed compute — not reserved capacity, not idle time.

JOBS PROCESSED
ALL TIME
SUCCESS RATE
99.9%
COMPLETED / TOTAL
CAPACITY
OPEN
AVAILABLE NOW · NO WAIT
JOBS · 30D
ROLLING WINDOW
FIG.01 · INFERENCE TOPOLOGY
SCALE 1:1
▶ Recent activity · /api/v1/jobs ○ IDLE
TIME JOB / MODEL REGION TOKENS STATUS
§02 · INTEGRATION

Drop-in replacement for your
OpenAI client.

Point your base_url at MicroDC.ai and keep the OpenAI client you already have. Stream the response or let it complete in the background. End-to-end encrypted payloads available for sensitive workloads.

API Reference Python SDK
# pip install openai
from openai import OpenAI

client = OpenAI(
    base_url="https://api.microdc.ai/v1",
    api_key=os.environ["MDC_KEY"],   # mDC_...
)

resp = client.chat.completions.create(
    model="llama3.3:70b",
    messages=[{"role": "user", "content": "..."}],
)

print(resp.choices[0].message.content)

Three audiences. One queue.

§03 · PATHS
01 · FOR DEVELOPERS

Asynchronous inference, no infrastructure to babysit.

REST, Python, OpenAI-compat. Submit jobs, get results. Encrypted payloads for sensitive workloads. Custom-amount credits — no minimums, no monthly fees.

  • REST · SDK · OpenAI-compat
  • LLM · embedding · document · Docker
  • End-to-end encryption (zero-knowledge results)
  • Pay per compute-second
02 · FOR ENTERPRISES

Cut the batch AI bill without a procurement cycle.

Shared team budgets, per-member spend caps, and private worker groups your jobs route to exclusively. Start on a credit card, move to an invoice when it matters.

  • Teams with shared credit pools
  • Monthly and per-member spend caps
  • Private worker groups
  • Results encrypted to your key
03 · FOR GPU OPERATORS

Idle silicon → revenue.

Connect a worker in five minutes. Context-tier routing means low-spec hardware still earns. Multi-GPU and concurrent jobs supported. Payouts in credits or PayPal.

  • 5-minute install
  • Context-tier routing
  • Multi-GPU · concurrent
  • Credits + bonus or USD

Mechanics, in four steps.

§04 · MECHANICS
STEP 01 ━━━▶

Submit

POST your job — model, payload, and optional encryption keys. You get a job id back immediately.

STEP 02 ━━━▶

Route

Our scheduler matches the job to a worker tier with the right VRAM, locality, and price ceiling.

STEP 03 ━━━▶

Execute

A worker pulls, runs, and returns. Streaming token deltas where applicable.

STEP 04

Deliver

Poll the job id, or let the SDK wait for you. Every job lands in your billing ledger with its own line item.

Workloads the queue is built for.

§05 · APPLICATIONS
DOC PIPELINESBATCH · OVERNIGHT

Document Processing

Summarize tens of thousands of PDFs, extract structure from contracts, normalize OCR output. Queue at 2am, deliver at 6am.

RESEARCHPARALLEL GRIDS

Research & Analysis

Run grids of experiments across model × prompt × dataset. No reservation, no spin-up time, no idle burn.

ENRICHMENTWAREHOUSE-SCALE

Data Enrichment

Classify, tag, embed, and score records at warehouse scale. Pull results back into your ETL on your own schedule.

GENERATIONNO RATE LIMITS

Content Generation

Personalized summaries, briefs, and translations. Rate-limit-free batches.

AUTOMATIONAPI-first

Automation Pipelines

Plug LLM steps into Airflow, Temporal, or n8n. Automatic retries, per-job cost on every line.

OVERNIGHT−74% cost

Overnight Processing

Submit during business hours, results on your morning desk. Cheapest tier.

§06 · ENGAGE

Plug in. Ship work.

No credit card to start. No monthly minimum. Free credits for evaluation, and a real person on the other end when you are sizing something larger.