Directory · Model comparison
DeepSeek-V4-Pro vs Devstral 2
Side-by-side API economics and benchmarks. Per-1M input and output rates, context window, and verified metrics.
Tale of the tape
Head-to-head specs pulled from each model profile.
| Metric | DeepSeek-V4-Pro | Devstral 2 |
|---|---|---|
| Input cost / 1M | $1.32 | $0.40 |
| Output cost / 1M | $3.96 | $2.00 |
| Context window | 1,000,000 tokens | 256,000 tokens |
| MMLU score | — | — |
Cost verdict
Enter monthly input and output volumes to see total cost savings.
DeepSeek-V4-Pro
- Input: 1M × $1.32 = $1.32
- Output: 1M × $3.96 = $3.96
- Total
- $5.28
Devstral 2
- Input: 1M × $0.40 = $0.40
- Output: 1M × $2.00 = $2.00
- Total
- $2.40
Total cost savings
$2.88
Devstral 2 saves $2.88 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. DeepSeek-V4-Pro is the premium route (higher combined per-1M cost); Devstral 2 handles routine traffic.
All premium
DeepSeek-V4-Pro
$264.00
100% of input and output on the premium route
Routed stack
80% → Devstral 2
20% → DeepSeek-V4-Pro
$148.80
- Routine slice
- $96.00
- Premium slice
- $52.80
Monthly savings
$115.20
43.6% lower
Rates pulled from this page's model database entries (deepseek-v4-pro, devstral-2) — same per-1M input/output figures as Tale of the tape. Production routing needs quality gates and monitoring.
Related comparisons
More head-to-head model matchups.