NVIDIA NIM
Developer hub · fee not published
Unverified
About NVIDIA NIM
NVIDIA's API catalog of hosted model endpoints for prototyping plus downloadable NIM inference microservices for self-hosting on NVIDIA GPUs.
- Fee on tokens
- Not published
- Pricing model
- Hosted API endpoints free for NVIDIA Developer Program prototyping; production self-hosted NIM requires an NVIDIA AI Enterprise license from $4,500 per GPU per year (about $1 per GPU per hour in the cloud); no per-token price
- Bring your own key
- No
- Entry plan
- Usage based
- Hosting
- Hosted
Features stated: none found. Not stated: Fallbacks, Load balancing, Caching, Guardrails, Observability, Rate limits, Budgets, Prompts, OpenAI-compatible, Bring your own key, Data residency, Private networking.
The terms, in their words
- Markup
- Hosted API endpoints free for NVIDIA Developer Program prototyping; production self-hosted NIM requires an NVIDIA AI Enterprise license from $4,500 per GPU per year (about $1 per GPU per hour in the cloud); no per-token price
- Free tier
- Free inference endpoints for NVIDIA Developer Program members (prototyping only); 90-day NVIDIA AI Enterprise trial
- These licenses start at $4500 per GPU per year or ~ $1 per GPU per hour in the cloud. Pricing is based on the number of GPUs, not the number of NIMs.
- Members of the NVIDIA Developer Program have free access to NIM API endpoints for prototyping
- Using NIM in production requires an NVIDIA AI Enterprise license.
Source: docs.api.nvidia.com/nim/docs/product
NVIDIA NIM vsHugging Face InferenceCloudflare Workers AIHeliconeKong AI GatewayLiteLLMVercel AI Gateway
Sources: each gateway's own pricing page and docs, read by hand and fetched again every Monday. List prices: your contract may differ. Logos via logo.dev; trademarks belong to their owners.