Using DeepSeek V3.1 Terminus on NVIDIA NIM

Implementation guide · DeepSeek · DeepSeek

ServerlessOpen Weights

NVIDIA NIM exposes DeepSeek V3.1 Terminus through model ID deepseek-ai/deepseek-v3_1-terminus. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-21. Next refresh: weekly.

Quick Start

  1. 1
    Create an account at NVIDIA NIM and generate an API key.
  2. 2
    Use the NVIDIA NIM SDK or REST API to call deepseek-ai/deepseek-v3_1-terminus — see the documentation for request format.
  3. 3
    You'll be billed . See full pricing.
API PortalDocumentationPricing

Code Examples

See NVIDIA NIM documentation for integration details.

Pricing on NVIDIA NIM

Capabilities

Structured Outputs

About DeepSeek V3.1 Terminus

DeepSeek: DeepSeek V3.1 Terminus available via OpenRouter. Pricing: $0.21/1M input, $0.79/1M output.

Full model details →

Model Specs

Released2025-09-22
Parameters671B total, 37B active (MoE)
Context164k
ArchitectureDecoder Only

Also available on(3)

OpenRouter$0.21/1MVercel AI Gateway$0.27/1MNovita AI$0.27/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States