DeepSeek-V3.2-Think by AIHubMix — Specs, Pricing & Capabilities | whichllm

Model ID deepseek-v3.2-think

Provider AIHubMix

Family deepseek

Status -

Knowledge Cutoff 2024-07

Release Date 2025-12-01

Input Modalities text

Output Modalities text

Context Window 131000

Input Limit -

Output Limit 64000

Tool Calling Yes

Reasoning Yes

Structured Output -

Temperature Control Yes

Open Weights Yes

Input Cost / 1M tokens $0.30

Output Cost / 1M tokens $0.45

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -