Using Mistral Small 4 on NVIDIA NIM

Implementation guide · Mistral Small · MistralAI

ServerlessOpen Source

NVIDIA NIM exposes Mistral Small 4 through model ID mistralai/mistral-small-4-119b-2603. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-05-14. 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 mistralai/mistral-small-4-119b-2603 — 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

VisionMultimodalJSON / Tool use

About Mistral Small 4

Mistral Small 4 is a hybrid 119B MoE model unifying instruct, reasoning, and coding capabilities. Features configurable reasoning effort per request and native function calling with JSON output support.

Full model details →

Model Specs

Released2026-03-16
Parameters119B (6.5B active)
Context256k
ArchitectureMixture of Experts
Knowledge cutoff2025-06

More Models on NVIDIA NIM

Mistral Small 3.1 24B Instruct
All models on NVIDIA NIM →

Also available on(2)

Mistral AI Studio$0.10/1MOpenRouter$0.15/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States