Nvidia

Mistral Large 3 675B Instruct 2512

Name: Mistral Large 3 675B Instruct 2512
Brand: Nvidia

Canonical ID: nvidia/mistralai/mistral-large-3-675b-instruct-2512

More Nvidia models More mistral-large-3-675b-instruct family models

Flagship Mistral model for advanced reasoning, coding, and multilingual work

Reasoning: No Tool use: Yes Open weights

Overview

text image

Provider: Nvidia
Family: mistral-large-3-675b-instruct
Release date: 2025-12-02
Last updated: 2025-12-02
Input modalities: text, image
Output modalities: text

Pricing and Limits

Token pricing

Input: $0/1M
Output: $0/1M
Cached input: N/A

Context and output

Context window: 262,144
Max output tokens: 262,144
Qualified ID: nvidia/mistralai/mistral-large-3-675b-instruct-2512

Model Summary

Mistral Large 3 675B Instruct 2512 is a model listing in the Nvidia provider catalog. It is categorized under the mistral-large-3-675b-instruct family.

The model supports text, image modalities across input/output paths. Reported context capacity is 262,144. Pricing is listed at $0/1M input and $0/1M output.

Same Family: mistral-large-3-675b-instruct

Comparable models in the same family across providers.

Browse family

Model	Provider	Context	Input	Output	Flags
Mistral Large 3 675b Instruct 2512 nano_gpt/mistralai/mistral-large-3-675b-instruct-2512	NanoGPT	131,072	$1/1M	$2/1M	Tools

Mistral Large 3 675B Instruct 2512

Overview

Pricing and Limits

Token pricing

Context and output

Model Summary

More From Nvidia

Active Speaker Detection

bevformer

BGE M3

ByteDance-Seed/Seed-OSS-36B-Instruct

Codegemma 1.1 7b

Codegemma 7b

Codellama 70b

Codestral 22b Instruct V0.1

Same Family: mistral-large-3-675b-instruct