Mistral Small 3.2 24B Instruct

Mistral Small 3.2 24B Instruct is a model from Mistral AI. AnonRouter provides access through the serving providers listed above.

The catalog lists January 15, 2026 as its release date.

Listed input rates are $0.0938; output rates are $0.25, per million tokens. Rates and cache discounts vary by provider. Check the Providers section for the route you choose.

The model catalog lists a context window of 256,000 tokens and up to 16,384 output tokens. Individual providers can have lower limits; check their rows in the Providers section.

The catalog currently lists text for this model. Check the Features section for its advertised capabilities.

Tool calling is advertised for this model. The catalog does not advertise a dedicated reasoning mode.

Currently callable routes offer these privacy levels: Private. Privacy depends on the provider route. Check the privacy badge and route details before choosing a provider; the Privacy section explains the strongest available level.

Open it in Chat, or use the Quickstart button above for an API example with this model's ID, mistralai/mistral-small-3.2-24b-instruct. Available interfaces depend on the model's modality and provider.