M

Mistral AI: Voxtral Small

Mistral AI
Streaming Vision
0
Context
$4.00
Input /1M
$0.3000
Output /1M
N/A
Max Output
Run API Call Open in Chat

Mistral AI: Voxtral Small

Model Overview

Property Value
Model ID mistral/voxtral-small-latest
Provider Mistral AI
Category Audio
Released TBD
Status Active
Flagship No

Description

Voxtral Small is a audio processing model for speech synthesis and audio understanding. Developed by Mistral AI, this model is optimized for its specific use case category.

Specifications

Property Value
Context Window 0 tokens
Max Output Tokens N/A
Knowledge Cutoff N/A
Modalities Text
Speed Tier N/A
Quality Tier N/A

Pricing

Type Price
Input $4.00 per 1M tokens
Output $0.30 per 1M tokens

Capabilities

Capability Supported
Vision/Image Input No
Tool/Function Calling No
JSON Mode No
Streaming Yes
System Prompt Yes

Use Cases

  • Speech synthesis and text-to-speech
  • Audio transcription and processing
  • Voice generation
  • Audio enhancement and restoration
  • Sound design and generation

Strengths

  • Reliable and consistent performance
  • Well-documented and supported
  • Suitable for production use
  • Comprehensive capability set

Limitations

  • No vision or image input capability
  • Limited tool/function calling support
  • No guaranteed JSON output mode

Integration with LangMart

Gateway Support:

  • Type 1 (Full Platform): Yes
  • Type 2 (Cloud Gateway): Yes
  • Type 3 (Self-hosted): Yes

API Endpoint:

curl -X POST https://api.langmart.ai/v1/chat/completions \
  -H "Authorization: Bearer sk-your-api-key" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "mistral/voxtral-small-latest",
    "messages": [{"role": "user", "content": "Hello"}],
    "max_tokens": 1024
  }'

OpenAI Compatibility: Full compatibility with OpenAI API format.

Models in this category and from this provider are available in the LangMart marketplace.

Additional Resources

Data Source: LangMart Provider Models Database Last Updated: 2026-01-02