Directory · Model comparison
Devstral 2 vs GPT-5.6 Luna
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 | Devstral 2 | GPT-5.6 Luna |
|---|---|---|
| Input cost / 1M | $0.40 | $0.20 |
| Output cost / 1M | $2.00 | $1.20 |
| Context window | 256,000 tokens | 1,050,000 tokens |
| MMLU score | — | — |
Cost verdict
Enter monthly input and output volumes to see total cost savings.
Devstral 2
- Input: 1M × $0.40 = $0.40
- Output: 1M × $2.00 = $2.00
- Total
- $2.40
GPT-5.6 Luna
- Input: 1M × $0.20 = $0.20
- Output: 1M × $1.20 = $1.20
- Total
- $1.40
Total cost savings
$1.00
GPT-5.6 Luna saves $1.00 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. Devstral 2 is the premium route (higher combined per-1M cost); GPT-5.6 Luna handles routine traffic.
All premium
Devstral 2
$120.00
100% of input and output on the premium route
Routed stack
80% → GPT-5.6 Luna
20% → Devstral 2
$80.00
- Routine slice
- $56.00
- Premium slice
- $24.00
Monthly savings
$40.00
33.3% lower
Rates pulled from this page's model database entries (devstral-2, gpt-5-6-luna) — 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.