Mistral: Ministral 8B

mistralai/ministral-8b · Mistral AIUnmeasurable

Declared family: Mistral
Declared tokenizer tag: Mistral
Entered catalogue: 17 October 2024
Measurement: Errored: the provider failed during measurement
Evidence confidence: Unknown

What we checked

Four different kinds of evidence, and what each one showed

We checked	What we found	Where it came from
How it counts tokens	Not measured yet	we measured it
How its API is set up	A combination of settings no other listing in the catalogue uses	api_02e2c5d8
How much it can read and write	Reads up to 128,000 tokens at once	its own listing

Declared record

What the catalogue claims about this model

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...

Modalities: text->text
Declared tokenizer: Mistral
Prompt price: $0.11 / M tokens
Completion price: $0.11 / M tokens

Supported parameters

frequency_penaltymax_tokenspresence_penaltyresponse_formatseedstopstructured_outputstemperaturetop_p

defaults: {"temperature":0.3}

Catalogue entry

History

Every observation, kept as taken

17 October 2024Enters the OpenRouter catalogue declared as Mistral.

* Mistral: Ministral 8B no longer appears in the OpenRouter catalogue, first absent from the snapshot of 3 September 2026. The record stays because the measurements above were real when they were taken and this address has been published.