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.
Groq LPUGoogle TPU Ironwood
| Attribute | Groq LPU Groq | Google TPU Ironwood |
|---|---|---|
| Segment | Chips & Compute | Chips & Compute |
| Version | GroqCloud API | 7th-generation (Ironwood) |
| Entry cost | Pricing not published on current page. Custom/usage rates apply. | from $5.4/unit |
| Pricing tiers | GroqCloud Console Free Tier / Pay-As-You-Go free | 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 | canopylabs/orpheus-arabic-saudi · canopylabs/orpheus-v1-english · kimi-k2-instruct-0905 · Llama / Kimi / GPT-OSS · Llama 3.1 8B Instant · Llama 3.3 70B Versatile · llama-4-maverick-17b-128e-instruct · llama-4-scout-17b-16e-instruct · LPU v2 · meta-llama/llama-4-maverick-17b-128e-instruct · meta-llama/llama-4-scout-17b-16e-instruct · minimax-m2.5 · minimax/minimax-m2.5 · minimaxai/minimax-m2.5 · moonshotai/kimi-k2-instruct-0905 · openai/gpt-oss-120b · openai/gpt-oss-20b · openai/gpt-oss-safeguard-20b · Orpheus English · orpheus-arabic-saudi · orpheus-v1-english · Qwen 3.6 27B · qwen/qwen3-32b · qwen/qwen3-vl-32b-instruct · qwen3-32b · qwen3-vl-32b-instruct · Whisper V3 Large · whisper-large-v3 | Gemini · Google TPU Ironwood · Ironwood · Ironwood (TPU v7) · Ironwood TPU · Ironwood TPU (7th Generation) · TPU v7 · TPU7x · TPU7x (Ironwood) · XLA compiler |
| Context window | 131k | — |
| Public API | ||
| Routes models | ||
| Changes / 30d | 3 | 11 |
| Origin | Global | Global |
| Capabilities | deterministic latency, OpenAI-compatible API, open-model catalogue, batch API, Fast LLM inference, OpenAI Compatibility, Prompt Caching, Speech to Text | 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 |