Three-Lane GPU Race

Waiting for data. Start a run on any Thunder Compute instance and POST to /api/ingest.

no active run

A6000

$0.50/hr · 48GB

gpu-a6000

model

—

tok/s—

last 60s

use case

—

eval progress

—

latency

—

vram

—

$1.29/hr · 80GB

gpu-a100

model

—

tok/s—

last 60s

use case

—

eval progress

—

latency

—

vram

—

$2.49/hr · 80GB

gpu-h100

model

—

tok/s—

last 60s

use case

—

eval progress

—

latency

—

vram

—

Waiting for data. POST progress events to /api/ingest with header X-Ingest-Token.