Alibaba (Qwen) › Qwen3 30B A3B › Pricing
$0.12 / $0.50per 1M tokens in / out
#287on OpenRouter by tokens · 1.8B / week
Price sheetper 1M tokens
| Input | $0.12 | DeepInfra |
| Output | $0.50 | |
| Context · max output | 33K · 16K | tokens |
Where to buy1 provider · per 1M tokens
| Provider | Input | Output | Context |
|---|---|---|---|
| DeepInfra | $0.12 | $0.50 | — |
In Alibaba (Qwen)'s line-upper 1M in / out
| Qwen Plus 2025-01-12 | $0.12 / $0.29 | −27% |
| Qwen 3.5 Flash 2026-02-23 | $0.10 / $0.40 | −19% |
| QwQ 32B | $0.15 / $0.40 | −1% |
| Qwen3 30B A3B | $0.12 / $0.50 | this model |
| Qwen3.8 Flash | $0.15 / $0.47 | +7% |
| Qwen3.8 Omni Flash | $0.15 / $0.47 | +7% |
| Qwen3.5 Plus 2026-02-15 | $0.12 / $0.69 | +20% |
Cheaper for the same workvs Qwen3 30B A3B
| Claude Haiku 5.5 max | -7% | score ×6.6 | $0.21 |
| GPT-6 Luna max | -7% | score ×5.8 | $0.068 |
| MiMo v2.6 Flash thinkingOpen | -19% | score ×5.7 | $0.062 |
| Agnes 2.5 Pro Beta | -30% | score ×5.3 | $0.10 / $0.30 |
| Nemotron 3.5 Super VLOpen | -19% | score ×4 | $0.19 |
Pricing questions
How much does Qwen3 30B A3B cost?›
$0.12 per 1M input tokens and $0.50 per 1M output tokens.
Is Qwen3 30B A3B free to use?›
There is no free API tier, but the weights are open: you can run it on your own hardware for the cost of compute.
What is a cheaper alternative to Qwen3 30B A3B?›
Claude Haiku 5.5 at max effort costs -7% per task with a score ×6.6 on Humanity's Last Exam.