Direct API pricing comparison
GPT-5.6 Terra vs Mistral Small 4
Compare current direct API token prices and estimated monthly workload costs for GPT-5.6 Terra and Mistral Small 4.
2direct models
Pricing only.Mistral Small 4 is cheaper in 4 of 4 comparable standard workload presets below. This is a pricing comparison only; it does not rank model quality.
| Model | Input | Cached | Output | Context | Max output | Source |
|---|---|---|---|---|---|---|
GPT-5.6 TerraOpenAI · Direct API | $2 | $0.2 | $12 | 1.05M | 128K | Direct ↗ |
Mistral Small 4Mistral · Direct API | $0.15 | $0.015 | $0.6 | 256K | — | Direct ↗ |
Same workload, different API bill
These four presets use 30 active days, standard direct rates, no retries, no reasoning-token add-on, no cache writes, and the cached-input percentage shown in each row.
| Standard workload | GPT-5.6 Terra | Mistral Small 4 | Lower monthly estimate |
|---|---|---|---|
| Chat10,000/day · 2,000 in · 500 out · 25% cached | $2,730 | $159.75 | Mistral Small 4 by $2,570.25 / mo |
| Coding2,000/day · 12,000 in · 1,800 out · 55% cached | $2,023.2 | $119.34 | Mistral Small 4 by $1,903.86 / mo |
| Agent1,200/day · 32,000 in · 2,500 out · 65% cached | $2,036.16 | $125.71 | Mistral Small 4 by $1,910.45 / mo |
| Documents400/day · 180,000 in · 2,000 out · 15% cached | $4,024.8 | $294.66 | Mistral Small 4 by $3,730.14 / mo |
The main calculator includes batch mode, long-context rules, retries, reasoning tokens, cache writes, and other model-specific pricing logic that a static comparison cannot fully capture.