Mistral
MistralGen-2024
multimodal · Release Jan 15, 2024 · License n/a
A versatile multimodal model capable of processing and generating text, images, and audio. It enables seamless interactions across different formats.
Modalities
What goes in and what comes out.
Inputs
text
Outputs
text
Capabilities
text generation, image synthesis, audio generation, cross-modal tasks
Benchmarks snapshot
Structured JSON for reproducible comparisons.
{}Related on GenAIWiki
Same provider, tooling that cites the model, or prompts tuned for it.
Mistral
Mistral Large
Mistral Large supports up to 16k tokens with a response latency of 150ms, targeting enterprise-level applications and complex document understanding.
Mistral
Mixtral
Mixtral integrates large language processing with generative capabilities, managing up to 16,384 tokens while delivering high-quality content creation and response generation.