Using Mistral Large 3 675B Instruct on NVIDIA NIM

Implementation guide · Mistral Large · MistralAI

ServerlessOpen Source

NVIDIA NIM exposes Mistral Large 3 675B Instruct through model ID mistralai/mistral-large-3-675b-instruct-2512. Use the setup steps, sourced pricing, capabilities, and official provider links below to validate this route before deployment.

Last refreshed 2026-06-19. 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-large-3-675b-instruct-2512 — 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

VisionMultimodalStructured Outputs

About Mistral Large 3 675B Instruct

Mistral Large 3 675B Instruct is MistralAI's Mistral Large model. It offers a 128K-token context window and scores 70.2 on τ-bench.

Full model details →

Model Specs

Released2025-12-01
Parameters675B
Context128k
ArchitectureDecoder Only
Knowledge cutoff2024-11

More Models on NVIDIA NIM

Mistral Large
All models on NVIDIA NIM →

Also available on(5)

OpenRouter$0.50/1MAWS Bedrock$0.50/1MMistral AI Studio$0.50/1M
Compare all providers →

Provider

NVIDIA NIM

NVIDIA

Santa Clara, California, United States