Mercury 2 vs Qwen3-VL 30B-A3B
Prices checked
Qwen3-VL 30B-A3B takes 4 of 5 rounds against Mercury 2. It is also the cheaper of the two to run, at $0.19 per million tokens against $0.38.
Mercury 2
128k context · tool calling
$0.38/M tokensInception's own price · $0.20 per 1,000 pages
Qwen3-VL 30B-A3B
131k context · tool calling · reads images · open weights
$0.19/M tokensCheapest price, at Alibaba Cloud (China) · 9.1¢ per 1,000 pages
Maker's price in (lower wins)
$0.25/M
$0.20/M
Maker's price out (lower wins)
$0.75/M
$0.80/M
Cheapest price (lower wins)
none below the maker
$0.19/M at Alibaba Cloud (China)
Maker's price, blended (lower wins)
$0.38/M
$0.35/M
Cost per 1,000 pages (lower wins)
$0.20
9.1¢
Context
128k tokens
131k tokens
Open weights
no
yes
Tool calling
yes
yes
Structured output
yes
not published
Reads images
no
yes
Reasoning
yes
yes
Released
24 Feb 2026
1 Apr 2025
Providers selling it
10
19
Price we measure against
the maker's own
the maker's own
Trains on your prompts (no is better)
no provider to check
not published
Providers selling both · 4
Kilo Gateway$0.38 / $0.26
Nous Portal$0.38 / $0.26
OpenRouter$0.38 / $0.26
TrustedRouter$0.40 / $0.28
Mercury 2, then Qwen3-VL 30B-A3B, per million tokens.
Go further
Add a third or fourth model, or change the weighting, in the tool.
What moved this week
Merge Gateway · 39% dearer · $0.15 / $0.60 $0.11 / $0.43
Frequently asked
- Which is cheaper, Mercury 2 or Qwen3-VL 30B-A3B?
- Qwen3-VL 30B-A3B, at $0.19 per million tokens against $0.38 for Mercury 2, blended 3 in : 1 out, read on 21 Oct 2026.
- Where is each one cheapest?
- Mercury 2: nobody sells it below the maker's own price with a stated reason, so $0.38 is the number to beat. Qwen3-VL 30B-A3B: $0.19 at Alibaba Cloud (China).
- Can I buy both from one provider?
- Yes. 4 providers sell both: Kilo Gateway, Nous Portal, OpenRouter, TrustedRouter. The cheapest of them for the two together is Kilo Gateway.
- Which holds more context?
- Qwen3-VL 30B-A3B, at 131k tokens against 128k.
Prices exclude tax, read 21 Oct 2026 from each provider's own catalog. They are per M tokens, blended 3 in : 1 out, and a page is 600 tokens in and 60 out. Bars are scaled to the larger value in each row.
Related comparisons