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.
AWS Trainium2Google TPU Ironwood
| Attribute | AWS Trainium2 AWS | Google TPU Ironwood |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | Trainium2 | 7th-generation (Ironwood) |
| Entry cost | Pricing is not published on the page. Available via EC2 instances/UltraServers. | from $5.4/unit |
| Pricing tiers | — | On Demand (us-central1) $12 · DWS Flex-start (us-central1) $6 · DWS Calendar Mode (us-central1) $8.4 · 1-year Commitment (us-central1) $8.4 · 3-year Commitment (us-central1) $5.4 · On Demand (europe-west2) $13.2 · DWS Flex-start (europe-west2) $6 · DWS Calendar Mode (europe-west2) $8.4 |
| Model stack | AWS Trainium2 · Llama · Llama 3.1 · Llama 3.1 405B · Llama 3.3 · Llama 3.3 70B · Neuron compiler · Qwen3 · Stable Diffusion · Trainium2 | Gemini · Google TPU Ironwood · Ironwood · Ironwood (TPU v7) · Ironwood TPU · Ironwood TPU (7th Generation) · TPU v7 · TPU7x · TPU7x (Ironwood) · XLA compiler |
| Context window | — | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 7 | 11 |
| Origin | Global | Global |
| Capabilities | Trn2 UltraServer, 64-chip NeuronLink domain, Neuron SDK, Rainier cluster, Generative AI training, Generative AI inference, Up to 20.8 FP8 petaflops, 1.5 TB HBM3 memory | 9,216-chip pods, inference optimised, liquid cooled, JAX + PyTorch/XLA, Large-scale training, Reasoning and inference, 9,216 liquid-cooled chips per pod, 42.5 ExaFlops performance |