Route order log in sign up
1 pick your primary route

Qwen: Qwen3 32B

qwen/qwen3-32b · agent · 131k ctx · added 2025-04-28
$0.0823·0.3263 /M effective hit 1% 3.28B/d

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...

view
openrouter/qwen/qwen3-32b
Qwen: Qwen3 32B · agent · 131k ctx
3.28B/d 1% $0.0823·0.3263 – 1y
sticker
life 429 tok/d dp age
¢ ¢ᵉ ¢ⁱ ✓ ★
deepinfra/fp8
$0.0800·0.2800 $0.0800·0.2800ⁱ $0.0794·0.2734ᵉ 0% – – 92% ✓ 537ms 26t/s 3mo ·
♻
nebius/base
$0.1000·0.3000 · $0.1000·0.3000ⁱ $0.0998·0.2991ᵉ · 53% · – – – · ✓ 550ms · 15t/s · ✕2mo ·
tenstorrent/fp8
$0.1400·0.4000·0.0900 $0.1298·0.4000ⁱ $0.1275·0.3986ᵉ 20% – – 3.9% ✓ 1126ms 18t/s 1d ·
siliconflow/fp8
$0.1400·0.5700 $0.1400·0.5700ⁱ $0.1397·0.5696ᵉ 14% – – 4.5% ✓ 1230ms 32t/s 3mo ·
⚡
groq
$0.2900·0.5900·0.1450 · $0.2603·0.5900ⁱ $0.2591·0.5880ᵉ · 21% · – – – · ✓ 390ms · 43t/s · ✕2mo ·
requesty/alibaba/qwen3-32b
qwen3-32b · agent · 40k ctx
– $0.1000·0.3000 – 1y
hf/Qwen/Qwen3-32B
Qwen3-32B · agent · 40k ctx
– $0.0800·0.2800 – 1y
compare all models →