Voxtral Small 24B 2507

Provider: Mistral AI EU Official API price

Input price
$0.10
/ 1M tokens
Output price
$0.30
/ 1M tokens
Cache price
$0.01
/ 1M tokens (read)
Context
33K tokens
Max output 26K tokens

Overview

Mistral AI (EU) offers Voxtral Small 24B 2507 as a specialized mid-tier model. It is designed to handle workloads requiring direct audio processing, alongside robust structured output capabilities. The model targets applications that benefit from multimodal understanding and precise response formatting.

Strengths

  • Native audio processing capability for multimodal applications.
  • Reliable function-calling for integrating with external tools.
  • JSON-mode ensures structured and predictable outputs.
  • Features a very low cache read price of $0.01/M tokens.

Best use cases

  • Transcribing audio and extracting structured data for analysis.
  • Building AI agents that interact with external APIs via function calls.
  • Processing voice commands and returning structured JSON responses.
  • Developing multimodal applications combining audio and text processing.

Pricing position

Voxtral Small 24B 2507 is priced at $0.09999999999999999/M for input and $0.3/M for output tokens. This places its input cost similarly to Devstral Small 1.1, and above other Mistral AI models like Small 3 ($0.049999999999999996/M in) and Small 3.2 24B ($0.075/M in). Compared to similarly-priced peers like Gemini 2.5 Flash Lite and GPT-4.1 Nano, it offers an identical input cost but a slightly more competitive output price.

Caveats

The model's context window of 32000 tokens is moderate; several other Mistral AI models, such as Ministral 3 3B 2512 and Mistral Small 3.2 24B, offer much larger contexts up to 131072 tokens. For text-only workloads not requiring audio capabilities, other Mistral AI models provide significantly lower output costs, with Ministral 3 3B 2512 being $0.09999999999999999/M for output tokens. The maximum output token limit for this model is also currently unknown.

Notes drafted by an LLM from the figures on this page (2026-05-21) and rewritten when the price changes.

Key facts

Price basis
Official API price
Max output
26K tokens
Listed on OpenRouter
2025-10-30
Tracked since
2026-05-08
Last updated
2026-11-10

Features

AudioFunction callingJSON output

Monthly cost estimate

Scale Input (M) Output (M) Monthly
0.1M (hobby) 0.1 0.05 $0.03
1M (small app) 1 0.5 $0.25
10M (mid scale) 10 5 $2.50
100M (large) 100 50 $25.00

※ Cache and batch discounts not factored in. Detailed calculator

Official resources

Other models from Mistral AI

Similar-priced models

Source: OpenRouter API (mistralai/voxtral-small-24b-2507)