Qwen3 32B (Non-reasoning) API Pricing

Alibaba · released 2025-04-28

Pricing

$0.16
input / 1M tokens
0.016¢ / 1K
$0.64
output / 1M tokens
0.064¢ / 1K
$0.28
blended / 1M tokens
0.028¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.0272¢
RAG query4,000 in / 500 out0.096¢
Long document summary50,000 in / 1,000 out0.864¢
Code review of a 2k-line file30,000 in / 2,000 out0.608¢
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$8.16

Cost = (input tokens ÷ 1,000,000 × $0.16) + (output tokens ÷ 1,000,000 × $0.64).

Benchmarks

7.3
Intelligence
#367 of 533
Coding
19.7
Math
#190 of 249
Tokens/sec
Time to first token

Similar intelligence, lower price

ModelIntelligenceBlended $/1M
Llama 3.1 Instruct 8B6.9$0.028
Gemma 4 E4B (Reasoning)8.9$0.04
Sarvam 30B (high)6.6$0.047
Granite 4.2 3B9.1$0.052
Nova Micro5.9$0.061

Leaderboard neighbours

ModelIntelligenceBlended $/1M
Llama 3.1 Instruct 405B7.3
Llama 3.1 Nemotron Nano 4B v1.1 (Reasoning)7.3
Llama 3.3 Nemotron Super 49B v1 (Non-reasoning)7.3
Qwen3 32B (Non-reasoning)7.3$0.28
Qwen3 8B (Reasoning)7.3$0.66
Qwen3 VL 8B Instruct7.3$0.31
Claude 3.5 Sonnet (June '24)7.2$6.00

More from Alibaba

ModelIntelligenceBlended $/1M
Qwen3.8 Max (0902)45.4$3.00
Qwen3.8 Max40.2$3.00
Qwen3.8 2.4T A95B39.9$3.00
Qwen3.8-Flash-Next39.8$0.23
Qwen3.8 27B (xhigh)33.7$1.125
Qwen3.7 Max29.5$3.75
Qwen3.6 Max Preview28.4$2.925
Qwen3.6 Plus27.0$1.125

Count tokens & estimate cost for Qwen3 32B (Non-reasoning) See Qwen3 32B (Non-reasoning) on the leaderboard

Source: Artificial Analysis · last synced 2026-09-22

FAQ

Who develops Qwen3 32B (Non-reasoning)?

Qwen3 32B (Non-reasoning) is developed by Alibaba, released 2025-04-28.

How much does Qwen3 32B (Non-reasoning) cost per million tokens?

Qwen3 32B (Non-reasoning) costs $0.16 per 1M input tokens and $0.64 per 1M output tokens ($0.28 blended), per Artificial Analysis's official pricing data.

How does Qwen3 32B (Non-reasoning) rank on benchmarks?

Qwen3 32B (Non-reasoning) scores 7.3 on the Artificial Analysis Intelligence Index, ranking #367 of 533 models we track.

Is there a cheaper model with similar intelligence to Qwen3 32B (Non-reasoning)?

Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.28/1M for Qwen3 32B (Non-reasoning).

Where does this data come from?

Pricing and benchmark data for Qwen3 32B (Non-reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.