Model Information
| Slug | ministral-8b-latest |
|---|---|
| LLMs.txt | View |
| Release Date | December 4, 2025 |
| AIME 2025 | 0.787 |
| GPQA | 0.668 |
Organization
| Name | Mistral |
|---|---|
| Website | https://mistral.ai/ |
Model Description
Ministral 8B is an 8B parameter model featuring a unique interleaved sliding-window attention pattern for faster, memory-efficient inference. Designed for edge use cases, it supports up to 128k context length and excels in knowledge and reasoning tasks. It outperforms peers in the sub-10B category, making it perfect for low-latency, privacy-first applications.
Available at 4 Providers
| Provider | Type | Model Name | Original Model | Input ($/1M) | Output ($/1M) | Free | Actions | |
|---|---|---|---|---|---|---|---|---|
|
|
Mistral AI |
Ministral 8B (latest)
|
ministral-8b-latest
|
$0.10 | $0.10 | |||
|
|
Blackbox AI |
Code
|
blackboxai/mistral/ministral-8b
|
blackboxai/mistral/ministral-8b
|
$0.15 | $0.15 | ||
|
|
Vercel AI Gateway |
Ministral 8B
|
mistral/ministral-8b
|
$0.15 | $0.15 | |||
|
|
Airforce API |
ministral-8b-latest
|
ministral-8b-latest
|
- | - |