Qwen3 30B A3B 2507 Instruct API Pricing

Alibaba · released 2025-07-29

Pricing

$0.20
input / 1M tokens
0.020¢ / 1K
$0.80
output / 1M tokens
0.080¢ / 1K
$0.35
blended / 1M tokens
0.035¢ / 1K

What it actually costs

WorkloadTokensCost
Short chat reply500 in / 300 out0.034¢
RAG query4,000 in / 500 out0.12¢
Long document summary50,000 in / 1,000 out$0.0108
Code review of a 2k-line file30,000 in / 2,000 out0.76¢
1,000 chat replies/day for 30 days30,000 × (500 in / 300 out)$10.20

Cost = (input tokens ÷ 1,000,000 × $0.20) + (output tokens ÷ 1,000,000 × $0.80).

Benchmarks

7.5
Intelligence
#353 of 533
Coding
66.3
Math
#97 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
Hermes 4 - Llama-3.1 405B (Reasoning)7.5$1.50
Llama 3.1 Nemotron Ultra 253B v1 (Reasoning)7.5
NVIDIA Nemotron Nano 12B v2 VL (Reasoning)7.5$0.30
Qwen3 30B A3B 2507 Instruct7.5$0.35
Solar Pro 2 (Reasoning)7.5
Gemini 2.0 Flash-Lite (Feb '25)7.4
Granite 4.1 30B7.4

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 Instruct See Qwen3 30B A3B 2507 Instruct on the leaderboard

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

FAQ

Who develops Qwen3 30B A3B 2507 Instruct?

Qwen3 30B A3B 2507 Instruct is developed by Alibaba, released 2025-07-29.

How much does Qwen3 30B A3B 2507 Instruct cost per million tokens?

Qwen3 30B A3B 2507 Instruct costs $0.20 per 1M input tokens and $0.80 per 1M output tokens ($0.35 blended), per Artificial Analysis's official pricing data.

How does Qwen3 30B A3B 2507 Instruct rank on benchmarks?

Qwen3 30B A3B 2507 Instruct scores 7.5 on the Artificial Analysis Intelligence Index, ranking #353 of 533 models we track.

Is there a cheaper model with similar intelligence to Qwen3 30B A3B 2507 Instruct?

Yes — Llama 3.1 Instruct 8B scores similar intelligence (6.9) at $0.028/1M blended, versus $0.35/1M for Qwen3 30B A3B 2507 Instruct.

Where does this data come from?

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