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
| Attribute | Google TPU Ironwood | Cerebras WSE-3 Cerebras |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | v7 Ironwood | WSE-3 / Inference |
| Entry cost | from ~$1.2 per chip-hour | Free tier, then from $0.06 / M tokens |
| Pricing tiers | On-demand $1.2 | Free free · Pay-as-you-go $0.06 |
| Model stack | TPU v7 · XLA compiler | Llama / Qwen / GPT-OSS · WSE-3 |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 1 | 1 |
| Origin | Global | Global |
| Capabilities | 9,216-chip pods, inference optimised, liquid cooled, JAX + PyTorch/XLA | wafer-scale engine, record token/s on open models, CS-3 systems, training clusters |