mistral

Voxtral Small (latest)

voxtral

Instruct model with native audio input for speech understanding and tool use

Tool CallingAttachmentsOpen Weights

Context Window

32K

Max Output

32K

Temperature

Yes

Open Weights

Yes

Knowledge Cutoff

N/A

Released

2025-07-15

Last Updated

2025-07-15

Modalities

Input:TextAudio
→
Output:Text

Available Providers (3)

ProviderInput /1MOutput /1MCache Read /1MCache Write /1MReasoningStatus
LLMTRLLMTRRp 1.789Rp 5.365————
Eden AIEden AIRp 1.789Rp 7.153Rp 179———
Tempr GatewayTempr GatewayRp 1.789Rp 5.365————