Directory · Model comparison

Codestral vs DeepSeek-V4-Pro

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 Codestral DeepSeek-V4-Pro
Input cost / 1M $0.30 $1.32
Output cost / 1M $0.90 $3.96
Context window 128,000 tokens 1,000,000 tokens
MMLU score

Cost verdict

Enter monthly input and output volumes to see total cost savings.

Codestral

Input: 1M × $0.30 = $0.30
Output: 1M × $0.90 = $0.90
Total
$1.20

DeepSeek-V4-Pro

Input: 1M × $1.32 = $1.32
Output: 1M × $3.96 = $3.96
Total
$5.28

Total cost savings

$4.08

Codestral saves $4.08 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); Codestral handles routine traffic.

Premium model

DeepSeek-V4-Pro

$1.32 in · $3.96 out / 1M

View profile →

Economical model

Codestral

$0.30 in · $0.90 out / 1M

View profile →

All premium

DeepSeek-V4-Pro

$264.00

100% of input and output on the premium route

Routed stack

80%Codestral

DeepSeek-V4-Pro

$100.80

Routine slice
$48.00
Premium slice
$52.80

Monthly savings

$163.20

61.8% lower

Rates pulled from this page's model database entries (deepseek-v4-pro, codestral) — 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.