Voxtral Small 24B 2507

voxtral-small-24b-2507

Voxtral Small is an upgraded version of Mistral Small 3 that adds advanced audio understanding while preserving strong text performance. It handles speech transcription, translation, and audio comprehension, with audio input billed per million seconds.

Context: 32K tokens
Endpoint

Get API Key Compare

Pricing

Input$0.125 / 1M

Output$0.375 / 1M

Cache Write (5m)Not applicable

Cache Write (1h)Not applicable

Cache ReadNot applicable

Web Search$0 / 1M

Quick Start

Select an endpoint and copy a working example for this model.

Endpoint

python

from openai import OpenAI client = OpenAI(    api_key="YOUR_API_KEY",    base_url="https://api.apertis.ai/v1") response = client.chat.completions.create(    model="voxtral-small-24b-2507",    messages=[        {"role": "user", "content": "Hello!"}    ],    max_tokens=1024,    temperature=0.7) print(response.choices[0].message.content) # Optional: Enable context compression to reduce token usage# response = client.chat.completions.create(#     model="voxtral-small-24b-2507",#     messages=[{"role": "user", "content": "Hello!"}],#     extra_body={"compression": {"enabled": True, "model": "gpt-4.1-mini"}}# )

Supported Parameters

API docs

Common5 params

modelinputvoiceresponse_formatspeed

Extended2 params

instructionsstream_format

Cursor IDE Model IDs

Use these namespaced identifiers in Cursor IDE to avoid conflicts with built-in models.

voxtral-small-24b-2507

Compare with Other Models

See how this model compares to others from the same provider.

Mistral Small Creative

Mistral Small Creative is an experimental lightweight model focused on creative writing and storytelling. It excels at narrative generation, roleplay, character dialogue, and general instruction-following for conversational agents.

Context: 32.8K
Input: $0.10/M
Output: $0.30/M

Mistral Small 4

Mistral Small 4 is the latest release in the Mistral Small family, unifying capabilities from multiple flagship models into a single system. It integrates strong reasoning (Magistral), multimodal understanding (Pixtral), and agentic coding capabilities (Devstral), enabling a versatile, all-in-one model. Designed to handle complex analysis, software development, and visual tasks within the same workflow, Mistral Small 4 is well suited for integrated agentic applications and end-to-end problem solving across domains.

Context: 262.1K
Input: $0.15/M
Output: $0.60/M

Mistral Medium 3.1

Mistral Medium 3.1 is an enterprise-grade update to Mistral Medium 3, delivering near–frontier reasoning and multimodal performance at much lower cost (up to 8× cheaper than large models). It excels in coding, STEM, and enterprise workflows, supports hybrid and on-prem deployments, and offers accuracy competitive with larger models like Claude Sonnet and Llama Maverick while remaining easy to integrate across cloud environments.

Context: 131.1K
Input: $0.40/M
Output: $2.00/M

Mistral Large 3 2512

Mistral Large 3 2512 is Mistral's most powerful model so far — a sparse MoE system with 41B active (675B total) parameters, released under the Apache 2.0 license.

Context: 262.1K
Input: $0.05/M
Output: $1.50/M