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.

Google TPU IronwoodCerebras WSE-3
AttributeGoogle TPU Ironwood

Google

Cerebras WSE-3

Cerebras

SegmentChips & ComputeChips & Compute
Versionv7 IronwoodWSE-3 / Inference
Entry costfrom ~$1.2 per chip-hourFree tier, then from $0.06 / M tokens
Pricing tiersOn-demand $1.2Free free · Pay-as-you-go $0.06
Model stackTPU v7 · XLA compilerLlama / Qwen / GPT-OSS · WSE-3
Context window
Public API
Routes models
Changes / 30d11
OriginGlobalGlobal
Capabilities9,216-chip pods, inference optimised, liquid cooled, JAX + PyTorch/XLAwafer-scale engine, record token/s on open models, CS-3 systems, training clusters