Every host for Qwen3 Coder 30B A3B Instruct
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| Novita | $0.12 | $0.07 | $0.27 | — | — | — |
| SiliconFlow | $0.123 | $0.07 | $0.28 | — | fp8 | 97.9% |
| Amazon Bedrock | $0.262 | $0.15 | $0.60 | — | — | 100.0% |
| Fireworks | $0.262 | $0.15 | $0.60 | — | — | — |
| Scaleway | $0.35 | $0.20 | $0.80 | — | — | — |
| Pinstripes | $0.375 | $0.30 | $0.60 | — | — | — |
Cheapest price over time
- Input
- Output
What your workload costs
- Novita$48.00
- SiliconFlow$49.00
- Amazon Bedrock$105.00
- Fireworks$105.00
- Scaleway$140.00
- Pinstripes$150.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 141B tokens/mo
- Needed around the clock
- 53.5K tok/s
8 × H100 cost $16,878 a month. The cheapest API (Novita) charges $0.12 per 1M blended tokens, so the GPUs only pay off above 141B tokens a month: the box must serve 53.5K tokens a second, every second.
GPU price: cheapest on-demand offer per GPU-hour × 730 hours. No throughput is assumed: it depends on the model size, precision, batch size and serving software, so measure yours. Power, storage, egress and engineering time are not included.
More from Qwen
Quality data: LMArena (CC BY 4.0), Epoch AI (CC BY 4.0). Prices: OpenRouter, LiteLLM (MIT), provider pages. List prices in US dollars before discounts and taxes; other currencies converted at the European Central Bank reference rate. The figures on these pages are free to reuse under CC BY 4.0 with a link to this page.