Directory · Model comparison
Codestral vs GPT-5.6 Terra
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-5.6 Terra |
|---|---|---|
| Input cost / 1M | $0.30 | $2.50 |
| Output cost / 1M | $0.90 | $15.00 |
| Context window | 128,000 tokens | 1,050,000 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-5.6 Terra
- Input: 1M × $2.50 = $2.50
- Output: 1M × $15.00 = $15.00
- Total
- $17.50
Total cost savings
$16.30
Codestral saves $16.30 per month vs the other model at this volume.
Model routing savings
Uses this page's verified rates. GPT-5.6 Terra is the premium route (higher combined per-1M cost); Codestral handles routine traffic.
All premium
GPT-5.6 Terra
$875.00
100% of input and output on the premium route
Routed stack
80% → Codestral
20% → GPT-5.6 Terra
$223.00
- Routine slice
- $48.00
- Premium slice
- $175.00
Monthly savings
$652.00
74.5% lower
Rates pulled from this page's model database entries (gpt-5-6-terra, 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.