Skip to content

Mistral AI · Chat

Mistral Medium

Mistral AI 🇫🇷ChatMistral familyOpen weights. One of its sources says the weights are publicly available.

Official mistral-medium-latest Mistral model

llminfo IQ
114.7
Maker's price
$3.00 blended / 1M
Max context
262K
Listings
17

Evidence and sources

llminfo IQ 114.7, ranked among chat models. From 48 benchmarks. Plenty of data behind it.How llminfo IQ is computedCoding IQ 90.8, 95% interval 76–105. From 4 benchmark families across 2 sources. Little data behind it, so treat it as a rough estimate. Uses the model's best published results. It has its own scale, separate from llminfo IQ.How Coding IQ is computedPoor value (24.3). Costs more per task than its benchmark results predict. From 6 benchmarks with measured task costs. A fair amount of data behind it.How Value for money worksYap score: tokens used per coding task vs. models with the same resultsChatty (59 ±9). Generates more tokens than models with similar coding results. Measured at default effort. Little data behind it, so treat it as a rough estimate.Median 35,775 output tokens per task at default effort.How the Yap score worksReleased 11 Dec 2023Maker HQ: FR (according to Mistral AI's own website)
Sources: Mistral API data, LMArena data, Models.dev data, llminfo researchPrimary data from Mistral API from LMArena: name, family, variant from Models.dev: weights availability from llminfo research: release date

Advantages and trade-offs

Compared with 10 chat models, picked mainly by popularity and IQ

Advantages

Open weights available

The weights are public. 4 of the 8 peers that say either way have open weights.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionReasoningFunction calling

Listings

 Mistral AImistral-mediumSources: Helicone Costs data, LiteLLM data, Mistral API data262K$2.39cache read $0.15$7.17
 Tokenmixmistral-mediumSources: TokenMix data, TokenMix PricingNot published by the provider$0.372$1.86
 AihubmixAiHubmix-mistral-mediumSource: AIHubMix data docsNot published by the provider$0.40$2.00
 Flowdotmistral-mediumSource: FlowDot data128K$0.40$2.00
 Flowdotmistral-medium-latest · latestSource: FlowDot data128K$0.40$2.00
 Merge Gatewaymistral/mistral-medium-latest · latestSource: Models.dev data262K$0.40$2.00
 302aimistral-medium-latest · latestSource: 302.ai data128K$0.44$6.60
 RequestyInference by Mistral AImistral/mistral-medium-latest · latestSource: Requesty data131K$0.44$2.20
 Eden AIInference by Mistral AImistral/mistral-medium-2604 · 2604Source: Models.dev data262K$1.50cache read $0.15$7.50
 OpenRoutermistral-mediumSource: GenAI Prices dataNot published by the provider$2.75$8.10
Show all 15 listings

Showing 10 of 15: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

2 listings without a price are hidden.

Benchmarks

Named effort levels run from lowest to highest. Select a result to see its source details.

Human preference

General

Coding

Instruction following

Math

Reasoning

Science

Other

Data credits: Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · LMArena, CC BY 4.0 (licence)

Around the web

  • Medium is the new large. | Mistral AI
    Research Medium is the new large. May 7, 2025 By Mistral AI Back to Blog …Research Medium is the new large. May 7, 2025 By Mistral AI Back to Blog 3 min read Share this post At Mistral AI, we are continuously pushing the frontier for both open models ( Mistral Small , Mist…

    mistral.ai

  • Medium is the new large. | Mistral AI
    Recherche Medium is the new large. May 7, 2025 By Mistral AI Retour au blog …Recherche Medium is the new large. May 7, 2025 By Mistral AI Retour au blog 3 min de lecture Partager cet article At Mistral AI, we are continuously pushing the frontier for both open models ( Mistra…

    mistral.ai

  • Big news: Mistral Medium 3 now available on watsonx | IBM
    Artificial intelligence IT automation Big news: Mistral Medium 3 now available on watsonx Spherical digital …Artificial intelligence IT automation Big news: Mistral Medium 3 now available on watsonx Spherical digital circle for watsonx Author Maryam Ashoori VP of Product and Engineering, watsonx.governance …

    ibm.com

  • Mistral Medium 3.1 - Mistral AI | Mistral Docs
    Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs …Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs ⌘K Toggle theme Reach out Try Studio 1. 3. Models 5. Model Cards 7. Mistral Medium 3.1 Try in playground ↗ M…

    docs.mistral.ai

  • Mistral Medium 3.1 - Mistral AI | Mistral Docs
    Docs & API Search docs ⌘K Vibe Studio Inference & Models Admin Resources API Reference …Docs & API Search docs ⌘K Vibe Studio Inference & Models Admin Resources API Reference Search docs ⌘K Toggle theme Reach out Try Studio 1. 3. Inference & Models 5. Models 7. Mistral Medium 3.1 Try in…

    docs.mistral.ai

  • Mistral Medium 3.0 - Legal Center
    Legal Center Terms AI Governance ← Back to all models Mistral Medium 3.0 Includes Mistral …Legal Center Terms AI Governance ← Back to all models Mistral Medium 3.0 Includes Mistral Medium 3.0 and subsequent versions. Model Lifecycle Technical Documentation Model Lifecycle Release dates, ty…

    legal.mistral.ai

  • mistral-medium-3.5-128b Model by Mistral AI | NVIDIA NIM
    Section: > mistral-medium-3.5-128b Model by Mistral AI · NVIDIA NIM License and Terms of Use: …Section: > mistral-medium-3.5-128b Model by Mistral AI · NVIDIA NIM License and Terms of Use: GOVERNING TERMS: The trial service is governed by the NVIDIA API Trial Terms of Service. Use of this mode…

    build.nvidia.com

  • Mistral Medium 3 - Mistral AI | Mistral Docs
    Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs …Docs & API Search docs ⌘K Getting Started Models Products Developers Admin API Search docs ⌘K Toggle theme Reach out Try Studio 1. 3. Models 5. Model Cards 7. Mistral Medium 3 Mistral Medium 3 icon C…

    docs.mistral.ai

  • mistralai / mistral-medium-3-5-128b
    updatedAt: 2026-08-06T10:00:10.000Z mistralai / mistral-medium-3-5-128b Mistral Medium 3.5 128B Description Mistral Medium 3.5 is Mistral …updatedAt: 2026-08-06T10:00:10.000Z mistralai / mistral-medium-3-5-128b Mistral Medium 3.5 128B Description Mistral Medium 3.5 is Mistral AI's first flagship merged model. It is a dense 128B model wi…

    docs.api.nvidia.com

  • Mistral Medium 3.5 — NeMo-AutoModel - NVIDIA Documentation
    Skip to main content Back to top NeMo-AutoModel - Home NeMo-AutoModel - Home NeMo-AutoModel Choose …Skip to main content Back to top NeMo-AutoModel - Home NeMo-AutoModel - Home NeMo-AutoModel Choose version Search Ctrl + K GitHub Search Ctrl + K Vision Language Models (VLMs) Mistral Medium 3.5 Mist…

    docs.nvidia.com

Also known as: aihubmix-mistral-medium, mistral-medium-2604, mistral-medium-latest, mistral-medium-latest@eu, mistral/mistral-medium, mistral/mistral-medium-2604, mistral/mistral-medium-2604@eu, mistral/mistral-medium-latest, mistral/mistral-medium-latest@eu, mistralai/mistral-medium

Like this one. Tap or hover any dotted value, label or icon to see where it comes from and how it is measured. open details when tapped or hovered. How this data works