Methods to Entry Ministral 3 fashions with an API

Methods to Entry Ministral 3 by way of API

TL;DR

Ministral 3 is a household of open-weight, reasoning-optimized fashions obtainable in each 3B and 14B variants. The fashions assist multimodal reasoning, native operate and gear calling, and an enormous 256K token context window, all launched below an Apache 2.0 license.

You’ll be able to run Ministral 3 straight on Clarifai utilizing the Playground for interactive testing or combine it into your purposes by means of Clarifai’s OpenAI-compatible API.

This information explains the Ministral 3 structure, how one can entry it by means of Clarifai, and the way to decide on the best variant on your manufacturing workloads.

Introduction

Fashionable AI purposes more and more rely on fashions that may cause reliably, keep lengthy context, and combine cleanly into current instruments and APIs. Whereas closed-source fashions have traditionally led in these capabilities, open-source options are quickly closing the hole. 

Amongst globally obtainable open fashions, Ministral 3 ranks alongside DeepSeek and the GPT OSS household on the high tier. Relatively than concentrating on leaderboard efficiency on benchmarks, Ministral prioritises performances that matter in manufacturing, resembling producing structured outputs, processing massive paperwork, and executing operate calls inside stay programs.

This makes Ministral 3 well-suited for the calls for of actual enterprise purposes, as organisations are more and more adopting open-weight fashions for his or her transparency, deployment flexibility, and talent to run throughout various infrastructure setups, from cloud platforms to on-premise programs.

Ministral 3 Structure

Ministral 3 is a household of dense, edge-optimised multimodal fashions designed for environment friendly reasoning, long-context processing, and native or non-public deployment. The household at the moment consists of 3B and 14B parameter fashions, every obtainable in base, instruct, and reasoning variants.

Ministral 3 14B

The most important mannequin within the Ministral household is a dense, reasoning-post-trained structure optimised for math, coding, STEM, and different multi-step reasoning duties. It combines a ~13.5B-parameter language mannequin with a ~0.4B-parameter imaginative and prescient encoder, enabling native textual content and picture understanding. The 14B reasoning variant achieves 85% accuracy on AIME ’25, delivering state-of-the-art efficiency inside its weight class whereas remaining deployable on life like {hardware}. It helps context home windows of as much as 256k tokens, making it appropriate for lengthy paperwork and sophisticated reasoning workflows.

Ministral 3 3B

The 3B mannequin is a compact, reasoning-post-trained variant designed for extremely environment friendly deployment. It pairs a ~3.4B-parameter language mannequin with a ~0.4B-parameter imaginative and prescient encoder (~4B complete parameters), offering multimodal capabilities. Just like the 14B mannequin, it helps 256k-token context lengths, enabling long-context reasoning and doc evaluation on constrained {hardware}.

Key Technical Options

• Multimodal Capabilities: All Ministral 3 fashions use a hybrid language-and-vision structure, permitting them to course of textual content and pictures concurrently for duties resembling doc understanding and visible reasoning.
• Lengthy-Context Reasoning: Reasoning variants assist as much as 256k tokens, enabling prolonged conversations, massive doc ingestion, and multi-step analytical workflows.
• Environment friendly Inference: The fashions are optimised for edge and personal deployments. The 14B mannequin runs in BF16 on ~32 GB VRAM, whereas the 3B mannequin runs in BF16 on ~16 GB VRAM, with quantised variations requiring considerably much less reminiscence.
• Agentic Workflows: Ministral 3 is designed to work effectively with structured outputs, operate calling, and tool-use, making it appropriate for automation and agent-based programs.
• License: All Ministral 3 variants are launched below the Apache 2.0 license, enabling unrestricted business use, fine-tuning, and customisation.

Pretraining Benchmark Efficiency

Ministral 3 14B demonstrates robust reasoning capabilities and multilingual efficiency in comparison with equally sized open fashions, whereas sustaining aggressive outcomes on common data duties. It notably excels in reasoning-heavy benchmarks and exhibits stable factual recall and multilingual understanding.

Accessing Ministral 3 by way of Clarifai

Conditions

Earlier than runing  Ministral 3 with the Clarifai API, you’ll want to finish a number of fundamental setup steps:

1. Clarifai Account: Create a Clarifai account to entry hosted AI fashions and APIs.
2. Private Entry Token (PAT): All API requests require a Private Entry Token. You’ll be able to generate or copy one from the Settings > Secrets and techniques part of your Clarifai dashboard.
   

For extra SDKs and setup steerage, confer with the Clarifai Quickstart documentation.

Utilizing the API

The examples beneath use Ministral-3-14B-Reasoning-2512, the most important mannequin within the Ministral 3 household. It’s optimised for multi-step reasoning, mathematical drawback fixing, and long-context workloads, making it well-suited for long-document useecases and agentic purposes. Right here’s how one can make your first API name to the mannequin utilizing completely different strategies.

Python (OpenAI-Suitable)

Python (Clarifai SDK)

It’s also possible to use the Clarifai Python SDK for inference with extra management over era settings. Right here’s how one can make a prediction and generate streaming output utilizing the SDK:

Node.js (Clarifai SDK)

Right here’s how one can carry out inference with the Node.js SDK:

Playground

The Clarifai Playground allows you to shortly experiment with prompts, structured outputs, reasoning workflows, and performance calling with out writing any code.

Go to the Playground and select both:

• Ministral-3-3B-Reasoning‑2512
  

• Ministral-3-14B-Reasoning‑2512

Functions and Use Circumstances

Ministral 3 is designed for groups constructing clever programs that require robust reasoning, long-context understanding, and dependable structured outputs. It performs effectively throughout agentic, technical, multimodal, and business-critical workflows.

Agentic Utility 

Ministral 3 is effectively fitted to AI brokers that have to plan, cause, and act throughout a number of steps. It may possibly orchestrate instruments and APIs utilizing structured JSON outputs, which makes it dependable for automation pipelines the place consistency issues. 

Lengthy Context

Ministral 3 can analyze massive paperwork utilizing its prolonged 256K token context, making it efficient for summarization, info extraction, and query answering over lengthy technical texts. 

Multimodal Reasoning

Ministral 3 helps multimodal reasoning, permitting purposes to mix textual content and visible inputs in a single workflow. This makes it helpful for image-based queries, doc understanding, or assistants that have to cause over combined inputs.

Conclusion

Ministral 3 supplies reasoning-optimized, open-weight fashions which might be prepared for manufacturing use. With a 256K token context window, multimodal inputs, native instrument calling, and OpenAI-compatible API entry by means of Clarifai, it presents a sensible basis for constructing superior AI programs.

The 3B variant is right for low-latency, cost-sensitive deployments, whereas the 14B variant helps deeper analytical workflows. Mixed with Apache 2.0 licensing, Ministral 3 provides groups flexibility, efficiency, and long-term management.

To get began, discover the fashions within the Clarifai Playground or combine them straight into your purposes utilizing the API.