whichllm — Browse and compare AI model specs and pricing

Synthetic

DeepSeek V3.2

deepseek

Model ID hf:deepseek-ai/DeepSeek-V3.2
Provider Synthetic
Family deepseek
Status -
Knowledge Cutoff -
Release Date 2025-12-01
Input Modalities text
Output Modalities text
Context Window 162816
Input Limit 162816
Output Limit 8000
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.27
Output Cost / 1M tokens $0.40
Reasoning Cost / 1M tokens -
Cache Read Cost / 1M tokens $0.27
Cache Write Cost / 1M tokens $0.00