Cracked AI Engineering

DeepSeek V3.1

Nvidia

The DeepSeek V3.1 AI model by Nvidia offers developers a powerful tool with a context window of 128,000 tokens and advanced reasoning capabilities. With an output limit of 8,192 tokens and no open weights, this model is ideal for complex text input and function calling tasks. Priced at $0/M input and $0/M output tokens, it provides cost-effective solutions for a wide range of applications.

Key Specifications

Context Window

128K tokens

Max Output Tokens

8K tokens

Input Pricing

Free

per million tokens

Output Pricing

Free

per million tokens

Capabilities

  • Text Generation
  • Function Calling
  • Advanced Reasoning

Additional Details

Provider
Nvidia
Release Date
August 20, 2025
Advanced Reasoning
Supported
Supported Input Types
text

Compare with Similar Models