Ministral 3 8B 2512
Mistral released 2025-12-02
$0.150 per million tokens, balanced
Gemma 4 26B A4B is both better and cheaper.
It scores +17.1 higher and costs 8% less ($0.138/M against $0.150/M) on this workload — and it does everything this model does.
DeepSeek V4 Flash 0731 is cheaper still (30% less) but drops no image input.
Every price dimension
| Input | $0.150/M |
|---|---|
| Output | $0.150/M |
| Cached input | $0.015/M |
Independent scores
| Intelligence | 9 |
|---|---|
| Coding | 9.7 |
| Agentic | 1.2 |
Sources are listed separately rather than averaged. Across the 62 models both have scored they correlate at r = 0.806 — close agreement overall, but four models rank very differently between them, and a blended score would hide exactly those.
Capability
| Context window | 262K |
|---|---|
| Input modes | text, image |
| Tool use | yes |
| Reasoning | no |
Provenance
| Price source | openrouter.ai |
|---|---|
| Fetched | 2026-08-24 |
| Quality data | verified |
A balanced model in the Ministral 3 family, Ministral 3 8B is a powerful, efficient tiny language model with vision capabilities.