Workloads

A bounded catalog, one API.

Three currently offered workload lanes are listed below. Preview describes release stage, not live capacity or a latency commitment. Unreleased research candidates stay internal until their evidence is complete.

Featured workloads

Open-model workloads in current discovery. Availability is checked separately when a job is submitted.

Image upscale (4×)

Featured

PER IMAGE

Batch$0.0033

Priority$0.0066

ModelsLab Real-ESRGAN @ $0.0047

− 30% vs alternative

Preview

Transcription (Whisper)

Featured

PER AUDIO HOUR

Batch$0.25

Priority$0.50

OpenAI Whisper API @ $0.36

− 30% vs alternative

Live

Subtitle generation

Featured

PER VIDEO HOUR

Batch$0.32

Priority$0.63

AssemblyAI subtitles @ $0.45

− 30% vs alternative

Live

Also available

Compare the current unit-rate quote and measured fit for your own workflow. Reference prices are illustrative and do not guarantee savings, performance, or capacity.

Chat / LLM

PER 1M TOKENS

Batch$0.063

Priority$0.13

Hosted LLM APIs (token-priced; models and input/output rates differ)

Live

LoRA fine-tune

PER TRAINING MINUTE

Batch$0.055

Priority$0.11

Cloud GPU rental (hardware-minute pricing; throughput and utilization differ)

Preview

Vision Q&A / doc understanding

PER 1K IMAGES

Batch$0.35

Priority$0.70

Hosted multimodal APIs (token- or image-priced; resolution and quality differ)

Live