ORBITAL // DYSON
ORBITAL//OPEN-WEIGHT INFERENCE

The cheapest way to run open-weight AI. Guaranteed.

No one runs open models more efficiently than Dyson — so no one runs them cheaper. Find a lower published rate for the same model anywhere, and we'll match it, then hand you a $100 credit for the tip.

Price-match guaranteethe lowest rate — or we pay you
Beat our price on the same open-weight model and we match it on the spot, plus $100 in credit for reporting it. Terms & conditions apply.
from $0.08/M tokens price-matched, guaranteed $100 if you beat it
01

Two categories. One forced choice.

The inference market has bifurcated — token APIs racing cost-per-million to the floor on one side, serverless GPU clouds fighting over cold-start milliseconds on the other. Pick the API and you can't ship a custom container. Pick the cloud and you're wiring up model serving yourself.

Model-as-a-Service

Token APIs

Send a prompt, get an answer — but you're locked to their menu of models.

  • DeepInfra
  • Fireworks AI
  • Together AI
  • Replicate
Dyson
both orbits
one API key
Infrastructure-as-a-Service

Serverless GPU

Bring your own code and weights — but you own the serving stack and the scaling.

  • Runpod
  • Modal
  • Beam
  • BentoML
02

Everything both halves do — one control plane.

01

Token endpoints

Serverless inference for DeepSeek, Llama, Qwen and GLM — OpenAI-compatible, per-million pricing, zero contracts.

$0.08 / M IN · $0.16 / M OUT
02

Bring-your-own container

Ship a Dockerfile or define the environment in Python. Custom fine-tunes and agentic workflows the endpoint can't hold.

GPU PODS FROM $0.59 / HR
03

Snapshot cold starts

Memory-snapshot restore boots a warm GPU container in under 150ms. Your endpoint costs nothing between requests.

<150MS · SCALE-TO-ZERO
04

Multi-LoRA serving

Run hundreds of Low-Rank Adaptations concurrently on one base model — custom behavior without reloading weights.

FP4 / FP8 · H100 · B200
05

Bring your own cloud

Burst into your own AWS, GCP or bare metal for data sovereignty. SOC 2, ISO 27001, and a zero-retention I/O policy.

BYOC · ZERO-RETENTION
06

Global orbit routing

Requests route to the nearest of 31 regions in real time. Per-second billing, integrated logs, versioned rollbacks.

31 REGIONS · SUB-SECOND AUTOSCALE
03

One column checks every box.

The disruptors are excellent — at exactly one half of the job. Coverage synthesized from public platform documentation.

Capability Dyson DeepInfra Fireworks Together Runpod Modal Beam
Per-token model API
Bring-your-own container
Scale-to-zero billing api api api
Sub-200ms cold start <150ms
Multi-LoRA on one base ltd ltd
Bring-your-own cloud (BYOC)
Zero-retention · SOC 2 / ISO part part part part
04

Pay for compute that runs. Never compute that waits.

A bursty workload keeps a GPU idle 70–90% of the time. On an always-on plan you fund every one of those idle seconds.The efficiency play

Dyson restores from a memory snapshot in under 150ms, so scaling from zero is invisible to your users — and the meter only turns while a token is actually being generated.

Day-1 open weights
DeepSeek-V4-Pro reasoning DeepSeek-V4-Flash $0.08/M Llama 4 Qwen 3.5-397B Qwen 3.6-35B GLM-5.2 1M ctx Gemma 4 multimodal Flux image your fine-tune
05

The numbers, unrounded.

<150msCold start · snapshot restore
$0.08Token floor · per M input
$0.59GPU pods · per hr, from
31Regions · auto-routed
0→1K+Autoscale · sub-second
fp4/fp8Precision · H100 · B200
99.9%Uptime SLA · throughput
0Bytes retained · I/O

Stop choosing between cheap and yours.

One API key covers token endpoints and your own GPU containers. No contracts, no idle billing, no infra team.