ai.canshu.com
中文
VRAM Calculator Advisor & TCO API Pricing Compare Models Leaderboard GPUs

Search models, GPUs, and tools

↑↓ Navigate · Enter Open · ★ Watchlist prioritized ai.canshu.com
Mistral AI
Open-Weight Mistral AI · voxtral-small-2507 · Text+Audio+PDF

Voxtral Small Official Specifications, Pricing & Benchmarks

Voxtral Small (voxtral-small-2507) by Mistral AI, released 2025-07-15, featuring 32,768 context window, 32,000 max output tokens, and Text+Audio+PDF input.

📋 Voxtral Small Official API & System Card Specifications

Verified against official Mistral AI developer documentation & pricing

API Model ID: voxtral-small-2507

1. Identity & Capabilities

API Spec
API Model ID
voxtral-small-2507
Release Date
2025-07-15
Weight License
Open-Weight (API Spec)
Native Reasoning
—
Function Calling & JSON Schema
✅ 原生支持
Batch API 异步批处理
✅ Supported (50% off)

2. Context, Output & Modalities

Limits
Max Context Window
33,000 tokens (33K)
Max Output Tokens
32,000 tokens
Input Modalities
Text + Audio + PDF
Output Modalities
Text
Direct China Access
🌐 Global / OpenRouter
Deployment Mode
Open-Weight + Cloud API

3. Official Pricing & Cache

USD / 1M
Input / 1M Tokens
$ 0.1
Cached Input / 1M
$ 0.02 -80%
Output / 1M Tokens
$ 0.4

🎛️ Official Sampling & Reasoning Parameters

Recommended generation settings & API parameter constraints

Standard Generation Config
temperature=0.7 top_p=0.95 max_tokens=32,000

Closest Self-Hostable Open-Weight Alternatives to Voxtral Small

Open-weight models with full HuggingFace weights for private GPU / Mac deployment

Compare with these →

Frequently Asked Questions

Is Voxtral Small open-source or proprietary?

Voxtral Small (voxtral-small-2507) is a proprietary commercial model by Mistral AI. Weights and internal layer dimensions are undisclosed; it is accessed via cloud API.

What are the context limit and API pricing of Voxtral Small?

Voxtral Small supports 33K input context and 32,000 max output tokens, priced at $0.1/1M input ($0.02/1M cached) and $0.4/1M output.