Head to head
DeepSeek V4 ProvsQwen2.5 72B Instruct
For tasks, about a month.
Verdict · measured basis
Qwen2.5 72B Instruct costs $0.0002 per solved task against
DeepSeek V4 Pro at $0.21 — ▼ 1315x cheaper.
Over 200 tasks that is $42 a month.
On output token price alone Qwen2.5 72B Instruct looks 9.9x cheaper. The ranking holds, but the margin changes.
Verified pricing, pass rate and cost per solved task for DeepSeek V4 Pro and Qwen2.5 72B Instruct| Figure | DeepSeek V4 Pro | Qwen2.5 72B Instruct |
|---|
| Input $/Mtok | $1.32 | $0.36 |
|---|
| Output $/Mtok | $3.96 | $0.4 |
|---|
| Cached input $/Mtok | $0.044 | $0.36 |
|---|
| Pass rate | 43% | 53% |
|---|
| Cost per solved task | $0.21measured | $0.0002measured |
|---|
| Cost per month | $42 | $0.03 |
|---|
Cost per month against tasks per month · drag the marker
Solid measured · dashed modeled · dotted stale. The gap is the verdict.
Source: Artificial Analysis (artificialanalysis.ai) · verified 2026-08-21 · prices from each provider's pricing page; measured rows ignore the tier · Methodology · All models at these settings