qwen Open weights Reasoning

Qwen3 32B pricing & benchmarks

Released Apr 28, 2025 · served by 5 providers

Input / 1M tokens$0.080
Output / 1M tokens$0.280
Context window131K
Cached input
Intelligence index11.5
Coding index15.3
Agentic index1.8
1M in + 300K out$0.16

What Qwen3 32B is

Qwen3-32B is a dense 32.8B parameter causal language model from the Qwen3 series, optimized for both complex reasoning and efficient dialogue. It supports seamless switching between a "thinking" mode for...

Providers and prices for Qwen3 32B

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 $0.080 $0.280 41K fp8 99.7%
Nebius $0.100 $0.300 41K fp8 99.5%
Alibaba $0.104 $0.416 131K 0.0%
SiliconFlow $0.140 $0.570 131K fp8 87.4%
Groq $0.290 $0.590 131K 100.0%

Cheaper models in the same class

Models scoring within 4 points of Qwen3 32B on the Intelligence Index, but with a lower output price.

FAQ

How much does the Qwen3 32B API cost?

$0.080 per 1M input tokens and $0.280 per 1M output tokens. A typical workload of 1M input + 300K output tokens costs about $0.16.

Is Qwen3 32B free?

No. It is a paid model starting at $0.080 per 1M input tokens, though some providers offer trial credits.

Which provider is cheapest for Qwen3 32B?

DeepInfra at $0.080 input / $0.280 output per 1M tokens (fp8 quantization).

Can I self-host Qwen3 32B?

Yes — weights are published as Qwen/Qwen3-32B on Hugging Face, so you can run it on your own hardware.