qwen Open weights

Qwen3 30B A3B Instruct 2507 pricing & benchmarks

Released Jul 29, 2025 · served by 6 providers

Input / 1M tokens$0.048
Output / 1M tokens$0.193
Context window262K
Cached input
1M in + 300K out$0.11

What Qwen3 30B A3B Instruct 2507 is

Qwen3-30B-A3B-Instruct-2507 is a 30.5B-parameter mixture-of-experts language model from Qwen, with 3.3B active parameters per inference. It operates in non-thinking mode and is designed for high-quality instruction following, multilingual understanding, and...

Providers and prices for Qwen3 30B A3B Instruct 2507

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
StreamLakecheapest $0.048 $0.193 128K 99.8%
SiliconFlow $0.090 $0.300 262K fp8 96.9%
Nebius $0.100 $0.300 262K fp8 95.0%
CoreWeave $0.100 $0.300 262K bf16 99.7%
Alibaba $0.130 $0.520 131K 100.0%
Phala $0.150 $0.550 262K 36.9%

FAQ

How much does the Qwen3 30B A3B Instruct 2507 API cost?

$0.048 per 1M input tokens and $0.193 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.11.

Is Qwen3 30B A3B Instruct 2507 free?

No. It is a paid model starting at $0.048 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 30B A3B Instruct 2507?

StreamLake at $0.048 input / $0.193 output per 1M tokens.

Can I self-host Qwen3 30B A3B Instruct 2507?

Yes — weights are published as Qwen/Qwen3-30B-A3B-Instruct-2507 on Hugging Face, so you can run it on your own hardware.