BEAM

Models

Features

Rankings

Docs

New

Pro

LAUNCH APP

Use Mistral Models in Big-AGI.

Bring your own key: Mistral's API rates, no markup. Keys stay in your browser. Run Mistral in parallel with other models, then compare and merge the answers.

labs-leanstral-1-5

Leanstral 1.5

Codestral (2508)

Mistral Small (2603)

Mistral Large (2512)

Mistral setup guide

All supported Mistral models

ModelContextInputOutputReleased

labs-leanstral-1-5

NEW

A mid & post-trained version of mistral small 4 for Lean (260618 SFT)

262K

Jun 2026

Leanstral 1.5

NEW

A mid & post-trained version of mistral small 4 for Lean (260618 SFT)

262K

Jun 2026

mistral-medium-3-5

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

mistral-medium

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

Mistral Medium (2604)

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

mistral-medium-latest

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

mistral-vibe-cli-latest

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

mistral-vibe-cli-with-tools

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

Apr 2026

Mistral Small (2603)

Mistral Small 4.

262K

$0.15

$0.6

Mar 2026

Leanstral (2603)

A mid & post-trained version of mistral small 4 for Lean

197K

Mar 2026

magistral-small-latest

Mistral Small 4.

262K

$0.15

$0.6

Mar 2026

mistral-small-latest

Mistral Small 4.

262K

$0.15

$0.6

Mar 2026

mistral-vibe-cli-fast

Mistral Small 4.

262K

$0.15

$0.6

Mar 2026

Devstral 2 (latest)

Official devstral-2512 Mistral AI model

262K

$0.4

Dec 2025

Devstral 2 (2512)

Official devstral-2512 Mistral AI model

262K

$0.4

Dec 2025

Devstral 2 (latest)

Official devstral-2512 Mistral AI model

262K

$0.4

Dec 2025

Devstral 2 (latest)

Official devstral-2512 Mistral AI model

262K

$0.4

Dec 2025

Ministral 3b (2512)

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

131K

$0.1

Dec 2025

Ministral 14b (2512)

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

262K

$0.2

Dec 2025

Ministral 8b (2512)

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

262K

$0.15

Dec 2025

ministral-14b-latest

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

262K

$0.2

Dec 2025

ministral-3b-latest

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

131K

$0.1

Dec 2025

ministral-8b-latest

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

262K

$0.15

Dec 2025

mistral-large-latest

Official mistral-large-2512 Mistral AI model

262K

$0.5

$1.5

Dec 2025

Mistral Large (2512)

Official mistral-large-2512 Mistral AI model

262K

$0.5

$1.5

Dec 2025

Magistral Medium (2509)

deprecated

Our frontier-class reasoning model release candidate September 2025.

131K

Sep 2025

magistral-medium-latest

deprecated

Our frontier-class reasoning model release candidate September 2025.

131K

Sep 2025

Magistral Small (2509)

deprecated

Our efficient reasoning model released September 2025.

131K

$0.5

$1.5

Sep 2025

Mistral Medium (2508)

Update on Mistral Medium 3 with improved capabilities.

131K

$0.4

Aug 2025

Codestral (2508)

Our cutting-edge language model for coding released August 2025.

256K

$0.3

$0.9

Jul 2025

codestral-latest

Our cutting-edge language model for coding released August 2025.

256K

$0.3

$0.9

Jul 2025

mistral-code-fim-latest

Our cutting-edge language model for coding released August 2025.

256K

$0.3

$0.9

Jul 2025

mistral-code-latest

Our cutting-edge language model for coding released August 2025.

256K

$0.3

$0.9

Jul 2025

Voxtral Mini (2507)

deprecated

A mini audio understanding model released in July 2025

33K

$0.04

Jul 2025

voxtral-mini-latest

deprecated

A mini audio understanding model released in July 2025

33K

$0.04

Jul 2025

Voxtral Small (2507)

A small audio understanding model released in July 2025

33K

$0.1

$0.3

Jul 2025

voxtral-small-latest

A small audio understanding model released in July 2025

33K

$0.1

$0.3

Jul 2025

Mistral Small (2506)

deprecated

Our latest enterprise-grade small model with the latest version released June 2025.

131K

$0.1

$0.3

Jun 2025

mistral-medium-3

Official mistral-medium-latest Mistral AI model

262K

$1.5

$7.5

May 2025

Mistral Medium (2505)

Our frontier-class multimodal model released May 2025.

131K

$0.4

May 2025

open-mistral-nemo

deprecated

Our best multilingual open source model released July 2024.

131K

$0.15

Jul 2024

open-mistral-nemo-2407

deprecated

Our best multilingual open source model released July 2024.

131K

$0.15

Jul 2024

Open Mistral Nemo

deprecated

Our best multilingual open source model released July 2024.

131K

mistral-tiny-latest

deprecated

Our best multilingual open source model released July 2024.

131K

labs-leanstral-1-5

NEW

Jun 2026

A mid & post-trained version of mistral small 4 for Lean (260618 SFT)

262K · in - · out -

Leanstral 1.5

NEW

Jun 2026

A mid & post-trained version of mistral small 4 for Lean (260618 SFT)

262K · in - · out -

mistral-medium-3-5

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

mistral-medium

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

Mistral Medium (2604)

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

mistral-medium-latest

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

mistral-vibe-cli-latest

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

mistral-vibe-cli-with-tools

Apr 2026

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

Mistral Small (2603)

Mar 2026

Mistral Small 4.

262K · in $0.15 · out $0.6

Leanstral (2603)

Mar 2026

A mid & post-trained version of mistral small 4 for Lean

197K · in - · out -

magistral-small-latest

Mar 2026

Mistral Small 4.

262K · in $0.15 · out $0.6

mistral-small-latest

Mar 2026

Mistral Small 4.

262K · in $0.15 · out $0.6

mistral-vibe-cli-fast

Mar 2026

Mistral Small 4.

262K · in $0.15 · out $0.6

Devstral 2 (latest)

Dec 2025

Official devstral-2512 Mistral AI model

262K · in $0.4 · out $2

Devstral 2 (2512)

Dec 2025

Official devstral-2512 Mistral AI model

262K · in $0.4 · out $2

Devstral 2 (latest)

Dec 2025

Official devstral-2512 Mistral AI model

262K · in $0.4 · out $2

Devstral 2 (latest)

Dec 2025

Official devstral-2512 Mistral AI model

262K · in $0.4 · out $2

Ministral 3b (2512)

Dec 2025

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

131K · in $0.1 · out $0.1

Ministral 14b (2512)

Dec 2025

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

262K · in $0.2 · out $0.2

Ministral 8b (2512)

Dec 2025

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

262K · in $0.15 · out $0.15

ministral-14b-latest

Dec 2025

Ministral 3 (a.k.a. Tinystral) 14B Instruct.

262K · in $0.2 · out $0.2

ministral-3b-latest

Dec 2025

Ministral 3 (a.k.a. Tinystral) 3B Instruct.

131K · in $0.1 · out $0.1

ministral-8b-latest

Dec 2025

Ministral 3 (a.k.a. Tinystral) 8B Instruct.

262K · in $0.15 · out $0.15

mistral-large-latest

Dec 2025

Official mistral-large-2512 Mistral AI model

262K · in $0.5 · out $1.5

Mistral Large (2512)

Dec 2025

Official mistral-large-2512 Mistral AI model

262K · in $0.5 · out $1.5

Magistral Medium (2509)

deprecated

Sep 2025

Our frontier-class reasoning model release candidate September 2025.

131K · in $2 · out $5

magistral-medium-latest

deprecated

Sep 2025

Our frontier-class reasoning model release candidate September 2025.

131K · in $2 · out $5

Magistral Small (2509)

deprecated

Sep 2025

Our efficient reasoning model released September 2025.

131K · in $0.5 · out $1.5

Mistral Medium (2508)

Aug 2025

Update on Mistral Medium 3 with improved capabilities.

131K · in $0.4 · out $2

Codestral (2508)

Jul 2025

Our cutting-edge language model for coding released August 2025.

256K · in $0.3 · out $0.9

codestral-latest

Jul 2025

Our cutting-edge language model for coding released August 2025.

256K · in $0.3 · out $0.9

mistral-code-fim-latest

Jul 2025

Our cutting-edge language model for coding released August 2025.

256K · in $0.3 · out $0.9

mistral-code-latest

Jul 2025

Our cutting-edge language model for coding released August 2025.

256K · in $0.3 · out $0.9

Voxtral Mini (2507)

deprecated

Jul 2025

A mini audio understanding model released in July 2025

33K · in $0.04 · out $0.04

voxtral-mini-latest

deprecated

Jul 2025

A mini audio understanding model released in July 2025

33K · in $0.04 · out $0.04

Voxtral Small (2507)

Jul 2025

A small audio understanding model released in July 2025

33K · in $0.1 · out $0.3

voxtral-small-latest

Jul 2025

A small audio understanding model released in July 2025

33K · in $0.1 · out $0.3

Mistral Small (2506)

deprecated

Jun 2025

Our latest enterprise-grade small model with the latest version released June 2025.

131K · in $0.1 · out $0.3

mistral-medium-3

May 2025

Official mistral-medium-latest Mistral AI model

262K · in $1.5 · out $7.5

Mistral Medium (2505)

May 2025

Our frontier-class multimodal model released May 2025.

131K · in $0.4 · out $2

open-mistral-nemo

deprecated

Jul 2024

Our best multilingual open source model released July 2024.

131K · in $0.15 · out $0.15

open-mistral-nemo-2407

deprecated

Jul 2024

Our best multilingual open source model released July 2024.

131K · in $0.15 · out $0.15

Open Mistral Nemo

deprecated

Our best multilingual open source model released July 2024.

131K · in - · out -

mistral-tiny-latest

deprecated

Our best multilingual open source model released July 2024.

131K · in - · out -

44 models · sorted by release date · prices in USD per 1M tokens · refreshed every 30 minutesCompare every model across vendors ->

Get started in 3 steps

Create an API key at the Mistral console.

Paste it into Big-AGI's model settings.

Start chatting, or Beam it against other models and fuse the answers.

Running Mistral in Big-AGI

Add your Mistral API key and use Mistral's models at Mistral's own API rates. Big-AGI isn't a reseller: no markup, no intermediary, Mistral bills you directly.

Your key, your billing. Usage is billed by Mistral directly, nothing routes through us.
Deterministic runs. Set a random seed for reproducible output, plus temperature and top-p for everything else.
One clean model list. Mistral's API returns many aliases for the same model; Big-AGI folds them into one clean entry instead of a cluttered near-identical list.
Hosted or local. Use Mistral's hosted API, or run its open-weight models locally through Ollama or LM Studio, and switch between them mid-chat.

Why not just Le Chat?

Le Chat is Mistral's model in Mistral's interface. Big-AGI runs Mistral next to GPT, Claude, Gemini, and anything else you've connected, side by side in the same conversation, which Le Chat isn't built to do.

It also opens up what Le Chat hides: temperature, top-p, and a random seed for reproducible output are real API parameters, not settings we invented. Your keys stay in your browser instead of a Mistral account.

The billing model changes too: Mistral charges per token, so a light user can spend less in a month than a subscription costs, and a heavy user never hits an artificial cap, just a bill for tokens used. Beam parallel runs do cost more, the honest tradeoff for comparing models side by side.

Your keys and your data

Turn on Direct Connection under Mistral's Advanced settings and the browser calls Mistral directly, bypassing the Big-AGI server, whenever your key is client-side and Mistral's API allows it. Your keys stay in your browser. Chats are stored locally first and sync only if you turn it on. The AI Inspector shows the exact request before it goes out: model, parameters, token counts, and a cost estimate.

Mistral in Beam

Beam runs Mistral against GPT, Claude, Gemini, or any other model you've connected, in parallel, then hands you Fusions: several strategies that combine, cross-check, and synthesize the parallel answers, which beats just picking the best one. Parallel runs use more tokens than a single chat.

Bring your Mistral key. Keep control.

Your key, your data, your choice of model. Big-AGI is open source and self-hostable, so you can check exactly how Mistral is called.

Launch Big-AGI

<- All Models

Alibaba

Anthropic

AWS Bedrock

Azure

Cerebras

DeepSeek

Fireworks AI

Google Gemini

Groq

MiniMax

Mistral

Moonshot

NVIDIA

OpenAI

OpenRouter

Perplexity

Sakana AI

SpaceXAI

Together AI

Z.ai

BIG-AGI

Product

Features Models Controls What's new BEAM Technology

Resources

Documentation Discord GitHub

Company

Email Us Privacy Terms