Mistral Studio

Your AI production platform: the developer console and Mistral API.

Visit website

Mistral's developer console and API platform — keys, Playground, evaluations, agents, and SDKs to ship AI apps. Free mode; pay-as-you-go.

Mistral Studio console landing page

Mistral Studio console landing page

1 / 2

Overview

What is Mistral Studio?

Your AI production platform: the developer console and Mistral API.

Mistral Studio is Mistral AI's developer console and API platform — the place to generate API keys, test models in the Playground, run evaluations, and build with agents and SDKs.

The preview API for Mistral Large 4 is live here: list pricing of $1.36 per million input tokens and $4.18 per million output tokens, currently 50% off in a preview sale ($0.68/$2.09; cached input $0.07). The API supports function calling, structured outputs, document Q&A, batch inference, and the Agents and Conversations endpoints.

Organizations can set monthly spend limits per workspace, and billing is pay-as-you-go beyond the Free mode allowance — no separate subscription tiers for API usage.

Platforms and languages

Mistral Studio Availability

Platforms

Web

Languages

English

Capabilities

Mistral Studio Key Features

API Playground

Test models, tune parameters, and compare outputs in the browser before writing code.

Keys and workspace management

Generate API keys in Free mode; set organization and workspace-level spend limits.

Structured outputs and function calling

Large 4 supports structured outputs and function calling via /v1/chat/completions and /v1/conversations.

Agents and Conversations APIs

Build agents with /v1/agents and /v1/conversations, plus built-in tools.

Batch API

Asynchronous batch inference at a 50% discount; plus document Q&A and OCR endpoints.

Best for

Who uses Mistral Studio?

Developers and ML engineers

Call Mistral's API, test models in the Playground, and ship AI applications

Plans and access

Mistral Studio Pricing

Freemium

Free mode to start; API pay-as-you-go. Large 4 preview: $0.68/$2.09 per 1M tokens (50% sale off $1.36/$4.18 list).

Common questions

Mistral Studio FAQs

How do I get a Mistral API key?

Sign up at console.mistral.ai, activate Studio in Free mode, and follow the quickstart guide to generate your first key — about five minutes.

How is API usage billed?

Pay-as-you-go beyond the Free mode allowance. You can set monthly spend limits per organization and workspace; API access may pause if limits are exceeded.

Is there a discount for batch workloads?

Yes — the Batch API offers 50% off standard pricing, and Mistral Large 4 currently carries an additional 50% preview sale discount.

Reviews

See what the community thinks and share your experience.

—

Based on 0 ratings

Rating distribution

0
0
0
0
0

Leave a review

Sign in to rate

Community reviews

No reviews

No written reviews yet.

Explore by category

AI Development Infrastructure

View all AI Development Infrastructure websites
CleanOps preview
CleanOps

The all-in-one CRM solution designed specifically for cleaning service businesses. Manage schedules, invoices, customers, and expenses in one place.

AI Development Infrastructure

Explore by category

AI Apis Sdks

View all AI Apis Sdks websites
Antirion preview
Antirion

Self-hosted open-source AI gateway routing LLM traffic at 0.5 ms overhead, with budgets and guardrails.

AI Apis Sdks
Runcrate preview
Runcrate

On-demand GPUs and 200+ open models behind one API, launchable by your AI agent.

AI Apis Sdks

Explore by category

Llms Foundation Models

View all Llms Foundation Models websites
Inception preview
Inception

API platform for Mercury diffusion LLMs: flagship Mercury 3 reports 1,000+ tokens/sec with a 1M-token context, built for real-time AI agents.

Llms Foundation Models
DeepSeek preview Featured
DeepSeek

DeepSeek is an AI lab offering a free chat app, a low-cost API ($0.15/M input), and MIT-licensed open model weights, including the 1M-context V4.1-Flash family.

Llms Foundation Models
Nimble preview
Nimble

API-first decision model that turns text into calibrated probabilities for every allowed answer — yes/no, best choice, or grades — with no sampling.

Llms Foundation Models