qwen Open weights Reasoning

Qwen3 30B A3B pricing & benchmarks

Released Apr 28, 2025 · served by 3 providers

Input / 1M tokens$0.120
Output / 1M tokens$0.500
Context window131K
Cached input
1M in + 300K out$0.27

What Qwen3 30B A3B is

Qwen3, the latest generation in the Qwen large language model series, features both dense and mixture-of-experts (MoE) architectures to excel in reasoning, multilingual support, and advanced agent tasks. Its unique...

Providers and prices for Qwen3 30B A3B

The same model costs different amounts depending on who serves it. Prices are per 1M tokens, cheapest first. Uptime and throughput are OpenRouter's rolling measurements, not vendor claims.

ProviderInputOutputContext QuantUptime 24hThroughput
DeepInfracheapest $0.120 $0.500 41K fp8 99.8%
Alibaba $0.130 $0.520 131K 100.0%
NextBit $0.140 $0.550 33K fp8 98.9%

Qwen3 30B A3B benchmark results

Design Arena head-to-head results, as reported through the OpenRouter model API.

CategoryArenaRankEloWin rate
dataviz models #97 997 39%
uicomponent models #97 983 42.4%
gamedev models #105 954 33.8%
codecategories models #108 972 37.5%
website models #108 979 37.7%

FAQ

How much does the Qwen3 30B A3B API cost?

$0.120 per 1M input tokens and $0.500 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.27.

Is Qwen3 30B A3B free?

No. It is a paid model starting at $0.120 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 30B A3B?

DeepInfra at $0.120 input / $0.500 output per 1M tokens (fp8 quantization).

Can I self-host Qwen3 30B A3B?

Yes — weights are published as Qwen/Qwen3-30B-A3B on Hugging Face, so you can run it on your own hardware.