Mistral Large 3: Flagship Vision-Language Inference on Modular

Mistral Large 3 is a 675B MoE model with 41B active parameters, supporting text and vision tasks.

Deploy dedicated endpoint

Try in Playground

Example Usage

Input

Python


  from openai import OpenAI
  
  client = OpenAI(
      base_url="https://model.api.modular.com",
      api_key="<your_api_token>",
  )
  
  response = client.chat.completions.create(
      model="mistralai/Mistral-Large-3-675B-Instruct-2512",
      messages=[
          {"role": "system", "content": "You are a helpful assistant."},
          {"role": "user", "content": "Explain speculative decoding in 3 sentences."},
      ],
      stream=True,
  )
  
  for chunk in response:
      if chunk.choices[0].delta.content:
          print(chunk.choices[0].delta.content, end="")

Get your API token

Output

  Speculative decoding uses a smaller draft model to predict multiple
  tokens ahead, then verifies them against the full model in a single
  pass. Accepted tokens skip individual generation steps, improving
  throughput without sacrificing accuracy. It's most effective when the
  draft model closely matches the target model's distribution.

Input

Cute orange cartoon fox with a small brown backpack sitting on grass in a bright, colorful forest.

Output

  “The image shows a fox wearing a backpack in a forest.”

Model Details

Developed by
Mistral AI
Model family
mistralai/Mistral-Large-3-675B-Instruct-2512
Modality
LLM,
Vision,
Context Window
256K
Total Params
675B
Precision
FP8 / NVFP4
Deployment options
Shared, Dedicated, Self-hosted

Why choose Mistral Large 3 on Modular?

High performance, out of the box
Run leading open models with strong default performance and the ability to optimize down to the kernel — extracting more from every GPU.
Lower Infrastructure Costs
Deploy efficiently across NVIDIA and AMD hardware to reduce GPU count, increase throughput, and avoid expensive closed-model licensing.
Easy Integration
Integrate through an OpenAI-compatible endpoint, swap models freely, and scale across clouds or hardware without redesigning your application stack.

Want to self-host this model with our open source infrastructure?

Read How

🔥 Trending models

DeepSeek V4 Flash

DeepSeek V4 Flash is a 284B MoE model with 13B active parameters and a 1M context window, designed for fast, cost-efficient inference.

LLM

DeepSeek V4 Pro

DeepSeek V4 Pro is a 1.6T MoE model with 49B active parameters and a 1M context window, featuring hybrid attention for efficient long-context inference.

LLM

FLUX.2 Klein 9B

FLUX.2 [klein] 9B is a 9 billion parameter rectified flow transformer capable of generating images from text descriptions and supports multi-reference editing capabilities.

Image

GLM-5.1

GLM-5.1 by Zhipu AI is a 744B MoE model with 40B active parameters, optimized for long-horizon agentic engineering tasks.

LLM

Similar models

Phi-4

Phi-4 by Microsoft is a dense 14B parameter model for text generation.

LLM

Mistral Small 3.1 24B

Mistral Small 3.1 by Mistral AI is a dense 24B parameter model supporting text and vision.

LLM

Vision

DeepSeek V3.2

DeepSeek V3.2 is a 685B MoE model with 37B active parameters, excelling at code, math, and general reasoning tasks.

LLM

Gemma 3 12B

Gemma 3 12B by Google DeepMind is a dense 12B parameter model supporting text and vision.

LLM