# https://mistral.ai/news/voxtral/ # https://huggingface.co/mistralai/Voxtral-Small-24B-2507 # https://huggingface.co/mistralai/Voxtral-Small-24B-2507/blob/main/params.json # https://docs.mistral.ai/api/endpoint/chat # Native params specify 32768 positions, matching the card's 32k context. # Output is this shared-window ceiling: prompt + max_tokens must fit; no separate native output cap is published. name = "Voxtral Small 24B 2507" description = "Open audio-language model for speech transcription, audio understanding, and voice-driven tool use" family = "voxtral" release_date = "2025-07-15" last_updated = "2025-07-15" attachment = true reasoning = false temperature = true tool_call = true open_weights = true license = "Apache 2.0" [limit] context = 32_768 output = 32_768 [modalities] input = ["text", "audio"] output = ["text"] [[weights]] label = "Hugging Face" url = "https://huggingface.co/mistralai/Voxtral-Small-24B-2507"