Mistral AI
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...
Running this yourself: desktop gpu should be enough.
---
Quality Score
---
Arena ELO
8B
Parameters
128K
Context
This measures the amount of verifiable public evidence we have, not how capable the model is. A missing field means it has not been verified yet, not that its value is zero.
14 of 22 public signals
Sign in to join the discussion
0
Downloads
0
Likes
Oct 2024
Released
4/5 signals
1/4 signals
4/5 signals
1/4 signals
4/4 signals
Parameters
8B
Training compute
Not reported
Dataset scale
Not reported
Base model
Not reported
Source-reported access: Open weights (non-commercial) · Confident confidence
Gaps we are still tracking
Start with the simple view: the cheapest reliable option, the official provider price, and the best places to try or deploy this model. The detailed table stays below if you want the full pricing breakdown.
Official provider access is separated from brokers and routers, so the lowest price does not get confused with the first-party route.
| Provider | Access | Primary Price | Output $/M | Speed | TTFT |
|---|---|---|---|---|---|
| OpenRouterBest priced Source: openrouter | Broker / Router | $0.1100/M | $0.11 | --- | --- |