Mistral: Ministral 8B

mistralai/ministral-8b · Mistral AIUnmeasurable
Declared family
Mistral
Evidence confidence
Unknown
Declared tokenizer tag
Mistral
Entered catalogue
17 October 2024
Last tested
Not yet measured
Measurement
Errored: the provider failed during measurement

Evidence stack

Signals of different kinds, weighed together
SignalResultReference
Tokenizer signatureNot measured
API surfaceNo other entry shares this exact contractapi_02e2c5d8
Context and output128,000 context · – max outputdeclared
Reasoning contractNone declareddeclared
Serving providers observedNone recorded yet

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.

Cite this page as the evidence record for Mistral: Ministral 8B: the URL is stable, measurements are dated, and revisions append to the history above. Method: tokenizer fingerprinting, v1, 50 strings. The raw data behind every figure is on the data page.