A simple asynchronous job queue for distributed AI inference. Submit, route, execute, deliver — explained in detail below.
Validated, added to the distributed queue with model spec, input prompt, and config parameters.
Scheduler matches the job to suitable workers based on model requirements, GPU capabilities, and current load.
Workers pull jobs, load models (cached if available), execute inference, submit results back encrypted and authenticated.
Results stored; notifications via webhook or polling. Configurable retention period.
Save up to 90% vs dedicated GPU instances. Pay only for actual compute time, not idle resources.
Process thousands of jobs in parallel across the distributed worker network. No infrastructure to manage.
Simple API, comprehensive SDKs, detailed documentation. Start integrating in minutes.
Every job is labeled with a context tier (1–4) at submission based on prompt length. Workers declare a max_context_tier via heartbeat — the scheduler only sends them jobs they can run efficiently. Better latency everywhere; revenue opportunities for low-spec hardware.
| Tier | Prompt size | Default routing |
|---|---|---|
| Tier 1 | 0–1.5K chars | All workers |
| Tier 2 | 1.5K–6K chars | Workers with tier ≥ 2 |
| Tier 3 | 6K–24K chars | Workers with tier ≥ 3 |
| Tier 4 | 24K+ chars | Workers with tier 4 (high-end GPUs) |
Payload encrypted with AES-256-GCM before it leaves the client — the server stores ciphertext and never inspects, logs, or decrypts it. The payload key is escrowed only until acknowledgment and released only to the MicroDC-managed worker that claims the job. Results are encrypted to your public key: only you can read them, cryptographically. Full architecture writeup →
Symmetric key generated on your machine, payload encrypted with AES-256-GCM, your RSA public key sent for results. Your private key never leaves your machine.
Ciphertext stored as-is; the payload key is escrowed, never used, and handed only to the claiming worker — a MicroDC-managed node with the admin-approved encryption capability.
In-memory decryption, inference on a local model — then the result is encrypted with a fresh one-time key wrapped to your public key.
Client decrypts with the private key that never left your machine. All key material is deleted from the platform on acknowledgment.
Docker jobs get live log streaming and per-job heartbeats. Routes only to workers advertising the docker capability.
Provide Docker image name, optional args/env, script and code files as inputs.
Only workers advertising docker see container jobs. Image pulled and started.
Workers ping POST /jobs/{id}/heartbeat with log lines. Resets timeout for long runs.
Exit code, stdout/stderr, output files submitted. Local cache means faster subsequent runs.
Free credits to start. No credit card. Five minutes from signup to first job result.