Directory · Model comparison

Codestral vs GPT-4.1

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	GPT-4.1
Input cost / 1M	$0.30	$2.00
Output cost / 1M	$0.90	$8.00
Context window	128,000 tokens	1,047,576 tokens
MMLU score	—	—

Cost verdict

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

Monthly input tokens, in millions Monthly output tokens, in millions

Codestral

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

GPT-4.1

Input: 1M × $2.00 = $2.00; Output: 1M × $8.00 = $8.00
Total: $10.00

Total cost savings

$8.80

Codestral saves $8.80 per month vs the other model at this volume.

Model routing savings

Uses this page's verified rates. GPT-4.1 is the premium route (higher combined per-1M cost); Codestral handles routine traffic.

Premium model

GPT-4.1

$2.00 in · $8.00 out / 1M

View profile →

Economical model

Codestral

$0.30 in · $0.90 out / 1M

View profile →

Monthly input tokens (millions) Monthly output tokens (millions)

All premium

GPT-4.1

$500.00

100% of input and output on the premium route

Routed stack

80% → Codestral

20% → GPT-4.1

$148.00

Routine slice: $48.00
Premium slice: $100.00

Monthly savings

$352.00

70.4% lower

Rates pulled from this page's model database entries (gpt-4-1, 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.