← All comparisons

Qwen 2.5 72B vs DeepSeek V3: token pricing & cost compared (July 2026)

How Qwen 2.5 72B (Qwen) and DeepSeek V3 (DeepSeek) actually compare on price — input, output, and total monthly cost at the MAU you care about. Updated against live OpenRouter pricing.

Qwen

Qwen 2.5 72B

Input
$0.36 / 1M tokens
Output
$0.40 / 1M tokens
Output / Input ratio
1.1×
Context window
131.072K

DeepSeek

DeepSeek V3

Input
$0.20 / 1M tokens
Output
$0.80 / 1M tokens
Output / Input ratio
4.0×
Context window
131.072K

The short answer

Qwen 2.5 72B wins for output-heavy work (chat, generation). DeepSeek V3 wins for input-heavy work (RAG, summarisation, classification).

Token pricing side-by-side

Input ($/1M)Output ($/1M)$0$0.25$0.5$0.75$1
  • Qwen 2.5 72B
  • DeepSeek V3

Cost at your usage

Qwen 2.5 72B

Per call

$0.00038

Per user / mo

$0.0380

Total / mo

$38

DeepSeek V3

Per call

$0.00050

Per user / mo

$0.0500

Total / mo

$50

Qwen 2.5 72B is cheaper by $0.0120/user/month — a saving of $12/month at 1,000 MAU.

Total monthly bill across MAU

1005001K5K10K50K100K$0$2K$3K$5K$6K
  • Qwen 2.5 72B
  • DeepSeek V3

Same usage profile applied to both models; only the per-token price differs.

Run this against your real numbers

The mini-calculator above is a preview. Use the full tools to model power-user blast radius, gross margin, and 12-month spend forecasts.

Comparing Qwen 2.5 72B vs DeepSeek V3 on price alone never tells the whole story — output-token weighting, context length, and your usage profile change the answer dramatically. Use the calculators below for the full picture.

Related tools: All comparisons · Cost Per User Calculator · How to calculate LLM cost per user