MistralAI
Ministral 8B
Updated: August 2026
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...
Specifications
- Context
- 128K
- Input Modalities
- Text
- Output Modalities
- Text
- Input
- $0.11/M
- Output
- $0.11/M
Capabilities
TEXTWRITING
Similarly Priced Models
| Model | Provider | Context | Input Price | Output Price |
|---|---|---|---|---|
| Qwen3 VL 32B Instruct | Qwen | 131K | $0.104/M | $0.416/M |
| Qwen3 VL 8B | Qwen | 262K | $0.117/M | $0.455/M |
| Qwen3 8B | Qwen | 131K | $0.117/M | $0.455/M |
| GPT-5.6 Luna | OpenAI | 1M | $0.1/M | $0.6/M |
| GPT-5.6 Luna | OpenAI | 1M | $0.1/M | $0.6/M |