DeepSeek V3.1 Terminus by Nvidia — Specs, Pricing & Capabilities | whichllm

Model ID deepseek-ai/deepseek-v3.1-terminus

Provider Nvidia

Family deepseek

Status -

Knowledge Cutoff 2025-01

Release Date 2025-09-22

Input Modalities text

Output Modalities text

Context Window 128000

Input Limit -

Output Limit 8192

Tool Calling Yes

Reasoning Yes

Structured Output -

Temperature Control Yes

Open Weights No

Input Cost / 1M tokens -

Output Cost / 1M tokens -

Reasoning Cost / 1M tokens -

Cache Read Cost / 1M tokens -

Cache Write Cost / 1M tokens -