NVIDIA NIM model catalog updates remove older DeepSeek versions

NVIDIA's hosted inference catalog, accessible via a public endpoint without authentication, has recently removed older DeepSeek models such as DeepSeek-R1 and V3.1. The catalog now lists newer models like deepseek-ai/deepseek-v4-flash-0731 and deepseek-ai/deepseek-coder-6.7b-instruct. This change reflects DeepSeek's own retirement of older model generations. Developers are advised to query this endpoint before hardcoding model IDs to avoid errors, as it provides the most up-to-date information on available models in NVIDIA NIM. AI

IMPACT Developers using NVIDIA NIM should monitor the public model catalog endpoint to ensure their configurations remain up-to-date and avoid errors due to model retirements.

RANK_REASON The item discusses an update to a service's model catalog, which is a tool-related change rather than a core model release or research breakthrough.

Read on dev.to — LLM tag →

• DeepSeek
• deepseek-ai/deepseek-coder-6.7b-instruct
• deepseek-ai/DeepSeek-V4-Flash-0731
• DeepSeek-R1
• NVIDIA
• NVIDIA NIM
• V3.1

• infra
• model release

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →