Ministral-3-8B-Instruct-2512 vs Mistral Large
API pricing, benchmark indices and specs — updated 19 October 2026.
mistralai · A · Open weights
Params
8.9 B
Context
—
30d
94 K
apache-2.0 · commercial OK
mistralai · B · API-only
Input / 1M
$2.00
Output / 1M
$6.00
AA index
5.8
proprietary · 128K context
Specification comparison
Differences are highlighted; identical values are muted.
| Specification | Ministral-3-8B-Instruct-2512 | Mistral Large |
|---|---|---|
| Deployment | Open weights · also via API | API-only (closed weights) |
| Parameters | 8.9 B | n/a — API-only |
| Architecture | Mistral3ForConditionalGeneration | n/a — API-only |
| Context length | 262,144 | 128,000 |
| Licence | apache-2.0 | Proprietary |
| Commercial use | Allowed | Per API terms |
| Languages | 11 | n/a — API-only |
| Downloads 30d | 93,976 | n/a — API-only |
| Downloads all time | 1.2 M | n/a — API-only |
| Quantizations on the Hub | SAFETENSORS | n/a — API-only |
| Gated | No | n/a — API-only |
| First seen on the Hub | 2025-10-31 | n/a — API-only |
| API input price / 1M tokens | $0.15 | $2.00 |
| API output price / 1M tokens | $0.15 | $6.00 |
| Est. cost per 1M input + 1M output tokens | $0.30 | $8.00 |
| Cached input / 1M tokens | $0.015 | $0.20 |
| AA Intelligence Index | 5.5 | 5.8 |
| AA Coding Index | 9.7 | — |
| AA Agentic Index | 0.6 | — |
| Max output tokens | 209,715 | 102,400 |
| API providers | 1 | 1 |
| Tool calling | Yes | Yes |
| Reasoning mode | No | No |
API cost
Estimated cost of 1M input + 1M output tokens via OpenRouter
Ministral-3-8B-Instruct-2512
$0.30
Mistral Large
$8.00
Ministral-3-8B-Instruct-2512 is 26.7× cheaper at list price.
VRAM side by side
On RTX 4090 · 24 GB · 8K context unless noted
Ministral-3-8B-Instruct-2512 · fp16
24.8 GB / 24 GB