whichllm — Browse and compare AI model specs and pricing

Nebius Token Factory

DeepSeek-V3.2

models.dev synced record

Model ID deepseek-ai/DeepSeek-V3.2
Provider Nebius Token Factory
Family -
Status -
Knowledge Cutoff 2025-11
Release Date 2026-01-20
Input Modalities text
Output Modalities text
Context Window 163000
Input Limit 160000
Output Limit 16384
Tool Calling Yes
Reasoning Yes
Structured Output Yes
Temperature Control Yes
Open Weights Yes
Input Cost / 1M tokens $0.30
Output Cost / 1M tokens $0.45
Reasoning Cost / 1M tokens $0.45
Cache Read Cost / 1M tokens $0.03
Cache Write Cost / 1M tokens $0.38