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.

Premium model

Devstral 2

$0.40 in · $2.00 out / 1M

View profile →

Economical model

GPT-5.6 Luna

$0.20 in · $1.20 out / 1M

View profile →

All premium

Devstral 2

$120.00

100% of input and output on the premium route

Routed stack

80%GPT-5.6 Luna

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.