Mistral Large 4
MistralMistral's flagship model, combining a large 1,048,576-token context with image input.
Main uses: European-hosted deployments and multilingual workloads needing both long context and reasoning support.
What sets it apart: A 262,144-token max output, among the highest ceilings on this page, well above its 1M context's typical use.
In
$0.70
Out
$2.10
Blended
$1.05
Where to buy this model
1 access routes| Route | In | Out | Blended | vs |
|---|---|---|---|---|
| $0.70 | $2.10 | $1.05 | - |
● official API · ● cloud platform · ● inference host · USD per 1M tokens. Same model, different providers - price and quantization vary.
- Ctx
- 1.048576M
- max output
- 262K
- cache read /1M
- $0.07
- Family
- mistral
- Modalities
- text · image
- Features
- json · reasoning · tools
Live pricing, updated 2026-11-03.
Mistral models at a similar price
| Model | In | Out | Ctx |
|---|---|---|---|
| Codestral 2508 | $0.3 | $0.9 | 256K |
| Mistral Large 3 2512 | $0.5 | $1.5 | 262K |
| Devstral 2 2512 | $0.4 | $2 | 262K |
| Mistral Medium 3 | $0.4 | $2 | 131K |
| Mistral Medium 3.1 | $0.4 | $2 | 131K |
| Mistral Large 4 · this model | $0.7 | $2.1 | 1.048576M |