Activefrontierllm Proprietary

Mistral Large 2

by Mistral AI· Released July 2024· Cutoff January 2024

Mistral Large 2 is Mistral AI's flagship large language model, offering state-of-the-art reasoning, multilingual support, and advanced coding capabilities. It features a 128K context window and excels in nuanced tasks like instruction following and function calling, positioning itself as a strong competitor to GPT-4 and Claude 3.5 Sonnet.

Official Site API Docs

Input cost

$3.00 per 1M tokens

Output cost

$9.00 per 1M tokens

Context window

128K tokens

Max output

—

Modalities

text

License

proprietary

Capabilities

Function CallingCode GenerationMultilingual SupportJSON ModeStreamingReasoningInstruction Following

Best For

Complex reasoning, multilingual tasks, and advanced code generation requiring high accuracy and large context.

Strengths

Excellent multilingual performance across dozens of languages
Strong coding and reasoning benchmarks
Large 128K context window
Efficient inference with lower cost than many competitors

Limitations

No native vision or image input support
May still lag behind GPT-4 on some creative writing tasks
Smaller ecosystem and community compared to OpenAI models

Use Cases

Multilingual customer support chatbots

Advanced code generation and debugging

Complex document analysis and summarization

Legal and financial document processing

Scientific research assistance

Enterprise-grade RAG systems

Multilingual translation and localization

Improvements Over Previous Model

Significantly improved multilingual capabilities, covering dozens of languages
Enhanced coding performance with better accuracy on HumanEval and MBPP
Larger context window (128K vs 32K in Mistral Large)
Improved instruction following and reduced hallucination
Lower pricing compared to Mistral Large (2402)
Better function calling and JSON mode support

Back to all models