Qwen3 30B A3B 2507 (Reasoning) API Pricing

Alibaba · released 2025-07-30

Pricing

$0.20
input / 1M tokens
0.020¢ / 1K
$2.40
output / 1M tokens
0.240¢ / 1K
$0.75
blended / 1M tokens
0.075¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.082¢
RAG query4,000 in / 500 out0.2¢
Long document summary50,000 in / 1,000 out$0.0124
Code review of a 2k-line file30,000 in / 2,000 out$0.0108
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$24.60

Cost = (input tokens ÷ 1,000,000 × $0.20) + (output tokens ÷ 1,000,000 × $2.40).

Benchmarks

9.8
Intelligence
#260 of 533
12.1
Coding
#168 of 197
56.3
Math
#117 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
Granite 4.2 3B9.1$0.052
NVIDIA Nemotron Nano 9B V2 (Reasoning)7.4$0.07
Sarvam 105B (high)8.8$0.074

Leaderboard neighbours

ModelIntelligenceBlended $/1M
K2-V2 (high)9.9
North Mini Code9.9
Qwen3 VL 235B A22B Instruct9.9$0.70
Qwen3 30B A3B 2507 (Reasoning)9.8$0.75
o1-mini9.8
DeepSeek V3 03249.7$0.927
Ling 2.6 Flash9.7

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 30B A3B 2507 (Reasoning) See Qwen3 30B A3B 2507 (Reasoning) on the leaderboard

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

FAQ

Who develops Qwen3 30B A3B 2507 (Reasoning)?

Qwen3 30B A3B 2507 (Reasoning) is developed by Alibaba, released 2025-07-30.

How much does Qwen3 30B A3B 2507 (Reasoning) cost per million tokens?

Qwen3 30B A3B 2507 (Reasoning) costs $0.20 per 1M input tokens and $2.40 per 1M output tokens ($0.75 blended), per Artificial Analysis's official pricing data.

How does Qwen3 30B A3B 2507 (Reasoning) rank on benchmarks?

Qwen3 30B A3B 2507 (Reasoning) scores 9.8 on the Artificial Analysis Intelligence Index, ranking #260 of 533 models we track.

Is there a cheaper model with similar intelligence to Qwen3 30B A3B 2507 (Reasoning)?

Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.75/1M for Qwen3 30B A3B 2507 (Reasoning).

Where does this data come from?

Pricing and benchmark data for Qwen3 30B A3B 2507 (Reasoning) comes from Artificial Analysis (artificialanalysis.ai), synced daily. Last synced 2026-09-22.