Head to head

Compare products

Pick up to four tracked products. Everything below comes from the most recent snapshot, so the price and model rows are as fresh as the last crawl.

Cerebras WSE-3Google TPU Ironwood
AttributeCerebras WSE-3

Cerebras

Google TPU Ironwood

Google

SegmentChips & ComputeChips & Compute
VersionWSE-3 / Inferencev7 Ironwood
Entry costFree tier, then from $0.06 / M tokensfrom ~$1.2 per chip-hour
Pricing tiersFree free · Pay-as-you-go $0.06On-demand $1.2
Model stackLlama / Qwen / GPT-OSS · WSE-3TPU v7 · XLA compiler
Context window
Public API
Routes models
Changes / 30d11
OriginGlobalGlobal
Capabilitieswafer-scale engine, record token/s on open models, CS-3 systems, training clusters9,216-chip pods, inference optimised, liquid cooled, JAX + PyTorch/XLA