Ministral 8B
by Mistral AI · Released Oct 2024
Context
128K tokens (~64 books)
Input $/1M
$0.11
Output $/1M
$0.11
Type
text
License
Proprietary
Benchmarks
0 tested
Data as of
About
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...
No benchmark data available yet.
Recently Happened
Ministral 8B added
Aug 21, 2026
Links
Research
Documentation
Community
BenchGecko API
ministral-8b
Specifications
- Typetext
- Context128K tokens (~64 books)
- ReleasedOct 2024
- LicenseProprietary
- StatusActive
- Cost / Message~$0.000
Available On
Learn More
Share & Export
Frequently Asked Questions
Ministral 8B is a proprietary text AI model by Mistral AI, released in October 2024. Context window: 128K tokens.
Related Models
Qwen3 Coder Next FP8 · AlibabaQwen2.5 Coder 32B Instruct AWQ · AlibabaSpeaker Diarization Community 1 · PyannoteGemma 3 12B (free) · Google DeepMindQwen3 Next 80B A3B Instruct (free) · Alibaba QwenBenchmarks
Key facts · as of 2026-08-27
- Ministral 8B by Mistral AI. Not enough public benchmark scores to rank yet.
- List price $0.11 input · $0.11 output per 1M tokens (as of 2026-08-27).
How to cite · data as of 2026-08-27
Ministral 8B · benchmarks, pricing and providers. BenchGecko, data as of 2026-08-27. https://benchgecko.ai/model/ministral-8b
Credit "Source: BenchGecko" with a link. Prices per provider and Gecko Tests are BenchGecko data (CC BY 4.0); benchmark scores keep their original source, listed in the JSON. JSON · llms.txt · MCP