Ministral 8B

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.

ChatMistral128k tokens$0.1199 / $0.1199 · 1M

mistralai/ministral-8b

Context
128k tokens
Completion cap
—
Tools
No
JSON
Yes
Released
2024-10-17

Call it from Geek Hub

Same OpenAI SDK. Change the base URL and the model id.

curl https://api.geekhub.mx/v1/chat/completions \
  -H "Authorization: Bearer $GEEKHUB_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistralai/ministral-8b",
    "messages": [{"role": "user", "content": "Hola"}]
  }'
Get an API key

Frequently asked questions

What is Ministral 8B?
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. Ministral 8B runs on the Geek Hub API (OpenAI-compatible). Model id: mistralai/ministral-8b.
Is Ministral 8B free?
No. Input is $0.1199 per 1M tokens and output is $0.1199 per 1M tokens on Geek Hub (markup included).
What is the context length of Ministral 8B?
Ministral 8B has a 128k tokens context window.
Does Ministral 8B support tool calling and structured outputs?
Ministral 8B does not advertise tool calling on this endpoint. It also supports structured outputs via a JSON schema in response_format.
When was Ministral 8B released?
Ministral 8B was released on 2024-10-17.

More models from Mistral