Directory · Model comparison
DeepSeek-V4-Flash vs Mistral Medium 3.5
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-Flash | Mistral Medium 3.5 |
|---|---|---|
| Input cost / 1M | $0.44 | $1.50 |
| Output cost / 1M | $1.32 | $7.50 |
| 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-Flash
- Input: 1M × $0.44 = $0.44
- Output: 1M × $1.32 = $1.32
- Total
- $1.76
Mistral Medium 3.5
- Input: 1M × $1.50 = $1.50
- Output: 1M × $7.50 = $7.50
- Total
- $9.00
Total cost savings
$7.24
DeepSeek-V4-Flash saves $7.24 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. Mistral Medium 3.5 is the premium route (higher combined per-1M cost); DeepSeek-V4-Flash handles routine traffic.
All premium
Mistral Medium 3.5
$450.00
100% of input and output on the premium route
Routed stack
80% → DeepSeek-V4-Flash
20% → Mistral Medium 3.5
$160.40
- Routine slice
- $70.40
- Premium slice
- $90.00
Monthly savings
$289.60
64.4% lower
Rates pulled from this page's model database entries (mistral-medium-3-5, deepseek-v4-flash) — 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.