Hello NVIDIA Team,
I’m a developer trying to use the NVIDIA NIM API for testing. Many models return “404 Not found for account” error when I call them via https://integrate.api.nvidia.com/v1/chat/completions.
Account Info:
- Registered Email: winger35@163.com
- Organization: Personal
- API Key ID prefix: nvapi-uM0s…
Models that work (47 models, e.g. z-ai/glm-5.2, mistralai/mistral-large-3-675b-instruct-2512, google/gemma-4-31b-it, etc.)
Models that return “Not found for account”:
- nvidia/llama-3.1-nemotron-70b-instruct
- nvidia/llama-3.1-nemotron-51b-instruct
- nvidia/llama-3.1-nemotron-ultra-253b-v1
- nvidia/nemotron-4-340b-instruct
- nvidia/nemotron-4-340b-reward
- deepseek-ai/deepseek-v4-flash
- deepseek-ai/deepseek-coder-6.7b-instruct
- mistralai/codestral-22b-instruct-v0.1
- mistralai/mistral-7b-instruct-v0.3
- google/gemma-3-12b-it
- (and 33 more total)
I already have an active API Key and can access 47 models fine, but these 44 models return 404. When generating a new API Key, there is no checkbox for “Services Included” or “Public API Endpoints”.
Could you please enable the “Public API Endpoints” permission for my personal organization?
Thank you!