whichllm — Browse and compare AI model specs and pricing

Firmware

DeepSeek v3.2

deepseek

Model ID deepseek-v3-2
Provider Firmware
Family deepseek
Status -
Knowledge Cutoff 2024-07
Release Date 2024-12-26
Input Modalities text
Output Modalities text
Context Window 128000
Input Limit -
Output Limit 8192
Tool Calling Yes
Reasoning No
Structured Output -
Temperature Control Yes
Open Weights No
Input Cost / 1M tokens $0.58
Output Cost / 1M tokens $1.68
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.28
Cache Write Cost / 1M tokens -