Skip to content
Toolsummary LLM price ledger

Qwen 3 VL 30 B A3 B Thinking pricing

Source: openrouter · updated 2026-11-13

Short answer: Qwen 3 VL 30 B A3 B Thinking costs $0.290 per million input tokens and $1.00 per million output tokens. That is a 3:1 blended rate of $0.468 per million tokens, ranking it #345 of 827 tracked models by input price.
Input / 1M
$0.290
Output / 1M
$1.00
Output ÷ input
3.45×
Context window
262,144

Price breakdown

MetricUSD
Input, per 1M tokens$0.290
Output, per 1M tokens$1.00
Output ÷ input multiple3.45×
3:1 blended, per 1M tokens$0.468
Context window262,144 tokens
Vendorqwen

What a typical workload costs

Monthly volumeInput costOutput costTotal
1M in / 250K out$0.290$0.250$0.540
10M in / 2.5M out$2.90$2.50$5.40
100M in / 25M out$29.00$25.00$54.00

Other qwen models

ModelInputOutput
Qwen 3.7 Flash$0.030$0.130
Qwen 3.5 Flash 02 23$0.065$0.260
Qwen 3.5.9 B$0.077$0.114
Qwen 3 32 B$0.080$0.280
Qwen 3 Next 80 B A3 B Instruct$0.090$1.10

Compare against

Cheaper alternatives

Next cheaper option: GPT-5.4 Nano at $0.200 per 1M input tokens. Next step up: Minimax M2.5 at $0.270 per 1M input tokens.


Spotted a price that is out of date? Submit a correction.