Mistral Large 4 Preview
MistralProprietaryReleased Oct 6, 2026
Mistral Large 4 Preview ranks #100 on LMArena (1427.4); official output price $4.18 per 1M tokens.
Key metrics
Models ranked nearby
Sorted by Arena score| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 58 |  GPT-5.6 Luna | 1430.5 | 37.3 | $1.20 | – |
| 59 |  Grok 4.6 | 1427.8 | 44.3 | $6.00 | – |
| 60 |  MiMo V2.5 | 1427.6 | 25.2 | $0.28 | – |
| 61 | Mistral Large 4 PreviewThis page | 1427.4 | 38.4 | $4.18 | – |
| 62 |  DeepSeek V3.2 | 1424.5 | 16.0 | $0.42 | – |
| 63 | Mistral Medium 3.5 | 1420.7 | 14.2 | $7.50 | 160 |
| 64 | GPT-5.2 | 1416.2 | 30.4 | $14.00 | – |
More from Mistral
| # | Model | Arena | Intel. | Output $ | tok/s |
|---|---|---|---|---|---|
| 63 | Mistral Medium 3.5 | 1420.7 | 14.2 | $7.50 | 160 |
| – | Mistral Large | – | 5.8 | $12.00 | – |
Pricing
- Official API list price: $1.36 input and $4.18 output per 1M tokens (USD).
- At a typical 3:1 input-to-output ratio, the blended cost is about $2.07 per 1M tokens.
- Among 78 models with an output price, it is the #34 cheapest.
Sources & methodology
Mistral Large 4 Preview (Mistral): Arena 1427.4 (#100), Intelligence Index 38.4, $1.36 in / $4.18 out per 1M tokens. Data updated Oct 9, 2026.
- LMArena — Arena score, 95% confidence interval, votes and rank.
- Artificial Analysis — Intelligence / Coding Index, output speed and latency (medians).
- OpenRouter — Route prices, context length and listing date.
Arena scores use the Bradley-Terry model (not Elo); ± is the half-width of the 95% confidence interval. Latency figures are Artificial Analysis medians; for reasoning models, time to first token and to first answer include the thinking phase. Data syncs daily at 14:20 (UTC+8).
FAQ
What rank is Mistral Large 4 Preview right now?
Mistral Large 4 Preview is #61 on our leaderboard of 68 scored models (Arena score 1427.4); its raw LMArena rank is #100.
What does Mistral Large 4 Preview cost via API?
Input $1.36 / output $4.18 per 1M tokens (official API list price; the OpenRouter quote when no official price is available). At a typical 3:1 input-to-output ratio, the blended cost is about $2.07 per 1M tokens.
How close is Mistral Large 4 Preview to the models ranked next to it?
It is 0.2 points behind MiMo V2.5 (1427.6) and 2.9 points ahead of DeepSeek V3.2 (1424.5); gaps smaller than the confidence interval (±9.2) are not significant.
Is Mistral Large 4 Preview open source? Can it be self-hosted?
Mistral Large 4 Preview is a closed model, available only via official APIs or hosted services.