Model family · 14 versions tracked
Mistral: every version compared
Mistral: Mistral Small 4 currently leads the Mistral family with an Artificial Analysis Intelligence Index of 19.7. For the best value within the family, Mistral: Ministral 3 14B 2512 costs $0.20/1M tokens blended.
- Mistral: Mistral Small 4 - 19.7 intelligence · $0.26/1M
- Mistral: Mistral Large 3 2512 - 15.9 intelligence · $0.75/1M
- Mistral: Mistral Medium 3.1 - 14.7 intelligence · $0.80/1M
- Mistral: Ministral 3 14B 2512 - 11.2 intelligence · $0.20/1M
- Mistral: Ministral 3 8B 2512 - - intelligence · $0.15/1M
- Mistral: Ministral 3 3B 2512 - - intelligence · $0.10/1M
- Mistral: Voxtral Small 24B 2507 - - intelligence · $0.15/1M
- Mistral: Codestral 2508 - - intelligence · $0.45/1M
- Mistral: Mistral Medium 3 - - intelligence · $0.80/1M
- Mistral: Mistral Small 3 - - intelligence · $0.06/1M
- Mistral Large 2407 - - intelligence · $3.00/1M
- Mistral: Mixtral 8x22B Instruct - - intelligence · $3.00/1M
- Mistral: Mistral Nemo - - intelligence · $0.02/1M
- Mistral Large - - intelligence · $3.00/1M
| # | Model | Intelligence index | Price/1M blended |
|---|---|---|---|
| 01 | Mistral: Mistral Small 4 | 19.7 | $0.26 |
| 02 | Mistral: Mistral Large 3 2512 | 15.9 | $0.75 |
| 03 | Mistral: Mistral Medium 3.1 | 14.7 | $0.80 |
| 04 | Mistral: Ministral 3 14B 2512 | 11.2 | $0.20 |
| 05 | Mistral: Ministral 3 8B 2512 | - | $0.15 |
| 06 | Mistral: Ministral 3 3B 2512 | - | $0.10 |
| 07 | Mistral: Voxtral Small 24B 2507 | - | $0.15 |
| 08 | Mistral: Codestral 2508 | - | $0.45 |
| 09 | Mistral: Mistral Medium 3 | - | $0.80 |
| 10 | Mistral: Mistral Small 3 | - | $0.06 |
| 11 | Mistral Large 2407 | - | $3.00 |
| 12 | Mistral: Mixtral 8x22B Instruct | - | $3.00 |
| 13 | Mistral: Mistral Nemo | - | $0.02 |
| 14 | Mistral Large | - | $3.00 |
Mistral real usage share, over time
Ranked by current quality, not release date - this pipeline's data collection started recently, so "first tracked" timestamps don't reflect true historical release dates yet. The usage-share chart above is real, unaffected by that limitation.
Frequently asked questions
What is the best Mistral model?
Mistral: Mistral Small 4 currently leads the Mistral family with an Artificial Analysis Intelligence Index of 19.7.
How much real usage does Mistral get?
Mistral models account for 0.2% of real OpenRouter token volume as of the latest data.
