NVIDIA NIM logo

Nemotron Mini 4B Instruct Free API on NVIDIA NIM

Free API Verified
Catalog metadata matched Tool use models.dev metadata

Compact Nemotron model for efficient reasoning and deployable AI agents

Free APINVIDIA NIM nativeTool callingText
Context window 128K
Max output 8K
API format NVIDIA NIM native
Status Online
AI Recommendation

Should you use Nemotron Mini 4B Instruct?

Nemotron Mini 4B Instruct is listed for chat workloads and supports a 128K context window.

Use it when NVIDIA NIM's free tier is enough for evaluation, demos, or light production traffic.

Best for
  • Chat
Strengths & Weaknesses

Strengths

  • Long context window
  • Tool calling support
  • Open weights available
  • Live API verification available

Watch outs

  • Vision support is not listed
Pricing

Nemotron Mini 4B Instruct pricing per 1M tokens

Free tier listed
Input $0 per 1M tokens
Output $0 per 1M tokens
Free access Available NVIDIA NIM
Availability

Nemotron Mini 4B Instruct availability by provider

Current provider only

We only found this Nemotron Mini 4B Instruct listing on NVIDIA NIM in the current catalog. Use the related models section for nearby alternatives.

Provider Model listing Access Context API Limits
NVIDIA NIM Nemotron Mini 4B Instruct Free tier 128K Native Varies
View NVIDIA NIM setup guide →
Typical Use Cases

Nemotron Mini 4B Instruct use cases

Chat

Nemotron Mini 4B Instruct is tagged for chat in this catalog.

FAQ

Nemotron Mini 4B Instruct free API FAQ

Is Nemotron Mini 4B Instruct free to use?

Nemotron Mini 4B Instruct is listed with free API access on NVIDIA NIM, subject to the provider's quota and account policy.

What is the Nemotron Mini 4B Instruct model ID?

The model ID shown in this catalog is nvidia/nemotron-mini-4b-instruct.

What context window does Nemotron Mini 4B Instruct support?

The listed context window is 128K tokens with up to 8K output tokens.

More about Nemotron Mini 4B Instruct

Free Nemotron Mini 4B Instruct API.

For API keys, setup steps, and provider-level limits, see the NVIDIA NIM provider page.