Use Mistral Models in Big-AGI.
Bring your own key: Mistral's API rates, no markup. Keys and chats stay in your browser. Run Mistral in parallel with other models, then compare and merge the answers.
All supported Mistral models
mistral-medium-3.5
Official mistral-medium-latest Mistral AI model
262K
-
-
Apr 2026
Mistral Medium (latest)
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-small-latest
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
Mistral Small (2603)
Mistral Small 4.
262K
$0.15
$0.6
Mar 2026
Devstral 2 (latest)
Official devstral-2512 Mistral AI model
262K
$0.4
$2
Dec 2025
Devstral 2 (2512)
Official devstral-2512 Mistral AI model
262K
$0.4
$2
Dec 2025
Devstral 2 (latest)
Official mistral-medium-latest Mistral AI model
262K
$0.4
$2
Dec 2025
Devstral 2 (latest)
Official devstral-2512 Mistral AI model
262K
$0.4
$2
Dec 2025
ministral-3b-latest
Ministral 3 (a.k.a. Tinystral) 3B Instruct.
131K
$0.1
$0.1
Dec 2025
ministral-8b-latest
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
262K
$0.15
$0.15
Dec 2025
Ministral 8b (2512)
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
262K
$0.15
$0.15
Dec 2025
ministral-14b-latest
Ministral 3 (a.k.a. Tinystral) 14B Instruct.
262K
$0.2
$0.2
Dec 2025
Ministral 3b (2512)
Ministral 3 (a.k.a. Tinystral) 3B Instruct.
131K
$0.1
$0.1
Dec 2025
Ministral 14b (2512)
Ministral 3 (a.k.a. Tinystral) 14B Instruct.
262K
$0.2
$0.2
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 Small (2509)
Our efficient reasoning model released September 2025.
131K
$0.5
$1.5
Sep 2025
magistral-medium-latest
Our frontier-class reasoning model release candidate September 2025.
131K
$2
$5
Sep 2025
magistral-small-latest
Mistral Small 4.
262K
$0.5
$1.5
Sep 2025
Magistral Medium (2509)
Our frontier-class reasoning model release candidate September 2025.
131K
$2
$5
Sep 2025
Mistral Medium (2508)
Update on Mistral Medium 3 with improved capabilities.
131K
$0.4
$2
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
Voxtral Small (2507)
A small audio understanding model released in July 2025
33K
$0.1
$0.3
Jul 2025
voxtral-mini-latest
A mini audio understanding model released in July 2025
33K
$0.04
$0.04
Jul 2025
Voxtral Mini (2507)
A mini audio understanding model released in July 2025
33K
$0.04
$0.04
Jul 2025
voxtral-small-latest
A small audio understanding model released in July 2025
33K
$0.1
$0.3
Jul 2025
Mistral Small (2506)
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
-
-
May 2025
Mistral Medium (2505)
Our frontier-class multimodal model released May 2025.
131K
$0.4
$2
May 2025
open-mistral-nemo
Our best multilingual open source model released July 2024.
131K
$0.15
$0.15
Jul 2024
open-mistral-nemo-2407
Our best multilingual open source model released July 2024.
131K
$0.15
$0.15
Jul 2024
mistral-medium
Official mistral-medium-latest Mistral AI model
262K
$0.4
$2
Dec 2023
Labs Leanstral 1 5 1
A mid & post-trained version of mistral small 4 for Lean (260618 SFT)
262K
-
-
-
Open Mistral Nemo
Our best multilingual open source model released July 2024.
131K
-
-
-
mistral-code-fim-latest
Our cutting-edge language model for coding released August 2025.
256K
-
-
-
mistral-vibe-cli-fast
Mistral Small 4.
262K
-
-
-
labs-leanstral-1-5
A mid & post-trained version of mistral small 4 for Lean (260618 SFT)
262K
-
-
-
mistral-tiny-latest
Our best multilingual open source model released July 2024.
131K
-
-
-
mistral-code-latest
Our cutting-edge language model for coding released August 2025.
256K
-
-
-
mistral-vibe-cli-with-tools
Official mistral-medium-latest Mistral AI model
262K
-
-
-
mistral-code-agent-latest
Official devstral-2512 Mistral AI model
262K
-
-
-
mistral-medium-3.5
Official mistral-medium-latest Mistral AI model
Mistral Medium (latest)
Official mistral-medium-latest Mistral AI model
mistral-medium-latest
Official mistral-medium-latest Mistral AI model
mistral-small-latest
Mistral Small 4.
Leanstral (2603)
A mid & post-trained version of mistral small 4 for Lean
Mistral Small (2603)
Mistral Small 4.
Devstral 2 (latest)
Official devstral-2512 Mistral AI model
Devstral 2 (2512)
Official devstral-2512 Mistral AI model
Devstral 2 (latest)
Official mistral-medium-latest Mistral AI model
Devstral 2 (latest)
Official devstral-2512 Mistral AI model
ministral-3b-latest
Ministral 3 (a.k.a. Tinystral) 3B Instruct.
ministral-8b-latest
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
Ministral 8b (2512)
Ministral 3 (a.k.a. Tinystral) 8B Instruct.
ministral-14b-latest
Ministral 3 (a.k.a. Tinystral) 14B Instruct.
Ministral 3b (2512)
Ministral 3 (a.k.a. Tinystral) 3B Instruct.
Ministral 14b (2512)
Ministral 3 (a.k.a. Tinystral) 14B Instruct.
mistral-large-latest
Official mistral-large-2512 Mistral AI model
Mistral Large (2512)
Official mistral-large-2512 Mistral AI model
Magistral Small (2509)
Our efficient reasoning model released September 2025.
magistral-medium-latest
Our frontier-class reasoning model release candidate September 2025.
magistral-small-latest
Mistral Small 4.
Magistral Medium (2509)
Our frontier-class reasoning model release candidate September 2025.
Mistral Medium (2508)
Update on Mistral Medium 3 with improved capabilities.
Codestral (2508)
Our cutting-edge language model for coding released August 2025.
codestral-latest
Our cutting-edge language model for coding released August 2025.
Voxtral Small (2507)
A small audio understanding model released in July 2025
voxtral-mini-latest
A mini audio understanding model released in July 2025
Voxtral Mini (2507)
A mini audio understanding model released in July 2025
voxtral-small-latest
A small audio understanding model released in July 2025
Mistral Small (2506)
Our latest enterprise-grade small model with the latest version released June 2025.
mistral-medium-3
Official mistral-medium-latest Mistral AI model
Mistral Medium (2505)
Our frontier-class multimodal model released May 2025.
open-mistral-nemo
Our best multilingual open source model released July 2024.
open-mistral-nemo-2407
Our best multilingual open source model released July 2024.
mistral-medium
Official mistral-medium-latest Mistral AI model
Labs Leanstral 1 5 1
A mid & post-trained version of mistral small 4 for Lean (260618 SFT)
Open Mistral Nemo
Our best multilingual open source model released July 2024.
mistral-code-fim-latest
Our cutting-edge language model for coding released August 2025.
mistral-vibe-cli-fast
Mistral Small 4.
labs-leanstral-1-5
A mid & post-trained version of mistral small 4 for Lean (260618 SFT)
mistral-tiny-latest
Our best multilingual open source model released July 2024.
mistral-code-latest
Our cutting-edge language model for coding released August 2025.
mistral-vibe-cli-with-tools
Official mistral-medium-latest Mistral AI model
mistral-code-agent-latest
Official devstral-2512 Mistral AI model
Get started in 3 steps
1
Create an API key at the Mistral console.
2
Paste it into Big-AGI's model settings.
3
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.
BIG-AGI
Resources
© 2026 Token Fabrics·Built with passion in San Diego