Directory · Model comparison
Codestral vs GPT-4o
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-4o |
|---|---|---|
| Input cost / 1M | $0.30 | $2.50 |
| Output cost / 1M | $0.90 | $10.00 |
| Context window | 128,000 tokens | 128,000 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
GPT-4o
- Input: 1M × $2.50 = $2.50
- Output: 1M × $10.00 = $10.00
- Total
- $12.50
Total cost savings
$11.30
Codestral saves $11.30 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. GPT-4o is the premium route (higher combined per-1M cost); Codestral handles routine traffic.
All premium
GPT-4o
$625.00
100% of input and output on the premium route
Routed stack
80% → Codestral
20% → GPT-4o
$173.00
- Routine slice
- $48.00
- Premium slice
- $125.00
Monthly savings
$452.00
72.3% lower
Rates pulled from this page's model database entries (gpt-4o, 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.