Directory · Model comparison

Codestral vs DeepSeek-V4-Flash

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-Flash
Input cost / 1M $0.30 $0.44
Output cost / 1M $0.90 $1.32
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-Flash

Input: 1M × $0.44 = $0.44
Output: 1M × $1.32 = $1.32
Total
$1.76

Total cost savings

$0.56

Codestral saves $0.56 per month vs the other model at this volume.

Model routing savings

Uses this page's verified rates. DeepSeek-V4-Flash is the premium route (higher combined per-1M cost); Codestral handles routine traffic.

Premium model

DeepSeek-V4-Flash

$0.44 in · $1.32 out / 1M

View profile →

Economical model

Codestral

$0.30 in · $0.90 out / 1M

View profile →

All premium

DeepSeek-V4-Flash

$88.00

100% of input and output on the premium route

Routed stack

80%Codestral

DeepSeek-V4-Flash

$65.60

Routine slice
$48.00
Premium slice
$17.60

Monthly savings

$22.40

25.5% lower

Rates pulled from this page's model database entries (deepseek-v4-flash, 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.