Average Ratings 0 Ratings
Average Ratings 0 Ratings
Description
Pixtral Large is an expansive multimodal model featuring 124 billion parameters, crafted by Mistral AI and enhancing their previous Mistral Large 2 framework. This model combines a 123-billion-parameter multimodal decoder with a 1-billion-parameter vision encoder, allowing it to excel in the interpretation of various content types, including documents, charts, and natural images, all while retaining superior text comprehension abilities. With the capability to manage a context window of 128,000 tokens, Pixtral Large can efficiently analyze at least 30 high-resolution images at once. It has achieved remarkable results on benchmarks like MathVista, DocVQA, and VQAv2, outpacing competitors such as GPT-4o and Gemini-1.5 Pro. Available for research and educational purposes under the Mistral Research License, it also has a Mistral Commercial License for business applications. This versatility makes Pixtral Large a valuable tool for both academic research and commercial innovations.
Description
TML-Interaction-Small is a multimodal interaction model created by Thinking Machines Lab that enables continuous real-time collaboration between humans and AI across audio, video, and text modalities. The model is designed to move beyond traditional turn-based AI systems by supporting native interaction capabilities such as simultaneous listening and speaking, proactive interjections, visual cue awareness, real-time responses, and ongoing contextual collaboration. TML-Interaction-Small processes interactions through a time-aligned micro-turn architecture that continuously exchanges 200ms streams of input and output, allowing the model to maintain conversational presence while reasoning, responding, and acting concurrently. The system combines an interaction model with an asynchronous background model that handles deeper reasoning, tool usage, browsing, and long-running workflows while the primary interaction layer continues communicating with the user in real time. The architecture allows users to collaborate with AI more naturally through speech, video, messaging, and multimodal inputs without waiting for rigid conversational turn boundaries. Thinking Machines Lab developed the model to improve human-AI collaboration by keeping people actively involved during AI workflows rather than relying solely on autonomous agents. TML-Interaction-Small includes capabilities such as live translation, contextual interruptions, visual-based reactions, concurrent speech processing, time awareness, tool calling, web browsing, and multimodal streaming interaction. The system also introduces encoder-free early fusion techniques, streaming inference optimization, and reinforcement learning strategies optimized for interactive responsiveness and stability.
API Access
Has API
API Access
Has API
Screenshots View All
No images available
Integrations
AI-FLOW
APIPark
Airtrain
Amazon Bedrock
Arize Phoenix
BlueGPT
Expanse
Graydient AI
Groq
Hyperbolic
Integrations
AI-FLOW
APIPark
Airtrain
Amazon Bedrock
Arize Phoenix
BlueGPT
Expanse
Graydient AI
Groq
Hyperbolic
Pricing Details
Free
Open source
Free Trial
Free Version
Pricing Details
No price information available.
Free Trial
Free Version
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Deployment
Web-Based
On-Premises
iPhone App
iPad App
Android App
Windows
Mac
Linux
Chromebook
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Customer Support
Business Hours
Live Rep (24/7)
Online Support
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Types of Training
Training Docs
Webinars
Live Training (Online)
In Person
Vendor Details
Company Name
Mistral AI
Founded
2023
Country
France
Website
mistral.ai/news/pixtral-large/
Vendor Details
Company Name
Thinking Machines Lab
Country
United States
Website
thinkingmachines.ai/