Mistral Small 3.2
mistral/mistral-small-2506
Efficient Mistral model for fast chat, extraction, and production assistants
Capabilities
ReasoningNo
Tool callingYes
Structured outputNo
TemperatureSupported
AttachmentNo
Open weightsYes
Limits
Context128,000 tokens
Max inputN/A
Max output16,384 tokens
Details
Familymistral-small
Knowledge cutoff2025-03
Release date2025-06-20
Last updated2025-06-20
Modalities
Inputtext, image
Outputtext
Community Rating
—
No ratings yet
Sign in to rate
Pricing
Cost per 1M tokens
InputN/A
OutputN/A