Every host for Qwen3 VL 30B A3B Instruct
| Host | Blended | Input | Output | Cached | Precision | Uptime |
|---|---|---|---|---|---|---|
| DeepInfra | $0.262 | $0.15 | $0.60 | — | fp8 | 99.7% |
| Fireworks | $0.262 | $0.15 | $0.60 | — | — | — |
| Novita | $0.325 | $0.20 | $0.70 | — | bf16 | 97.0% |
| SiliconFlow | $0.467 | $0.29 | $1.00 | — | fp8 | 85.6% |
Cheapest price over time
- Input
- Output
What your workload costs
- DeepInfra$105.00
- Fireworks$105.00
- Novita$130.00
- SiliconFlow$187.00
Rent GPUs or pay per token?
- Renting the GPUs
- $16,878/mo
- Break-even volume
- 64.3B tokens/mo
- Needed around the clock
- 24.5K tok/s
8 × H100 cost $16,878 a month. The cheapest API (DeepInfra) charges $0.262 per 1M blended tokens, so the GPUs only pay off above 64.3B tokens a month: the box must serve 24.5K 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.