Skip to content

Mistral AI · Chat

Ministral 3B

Mistral AI 🇫🇷ChatMinistral familyOpen weights. One of its sources says the weights are publicly available.The maker currently plans to deprecate it within the next 180 days (9 Dec 2026). Plans can change.

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

llminfo IQ
100.6
Maker's price
$0.04 blended / 1M
Max context
262K
Listings
30

Evidence and sources

🤗 mistralai/Ministral-3-3B-Instruct-2512llminfo IQ 100.6, ranked among chat models. From 24 benchmarks. Plenty of data behind it.How llminfo IQ is computedPoor value (38.6). Costs more per task than its benchmark results predict. From 1 benchmark with measured task costs. Little data behind it, so treat it as a rough estimate.How Value for money worksReleased 16 Oct 2024Maker HQ: FR (according to Mistral AI's own website)
All rankings: #244 on OpenRouter this week #249 on OpenRouter today #262 on OpenRouter this month #419 on NanoGPT recentlySources: Mistral API data, Models.dev data, GenAI Prices data, LiteLLM data, AI/ML API data, llminfo researchPrimary data from Mistral API from Models.dev: name, weights availability from GenAI Prices: family, variant from LiteLLM: deprecation date from AI/ML API: primary mode from llminfo research: release date
Tags from its sources:instructtoolsvision

Advantages and trade-offs

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

Advantages

Open weights available

The weights are public. 2 of the 6 peers that say either way have open weights.

Trade-offs

Deprecation scheduled

The maker plans to deprecate it on 9 Dec 2026, within the next 180 days.

We only make a claim when there's enough data on models of the same type. Updated 22 Nov, 04:34 UTC.Prices come from the model's maker where they sell it, otherwise their official partner, otherwise the market median. This comparison uses 6 maker's prices; 3 market median prices.

Input & output

as stated by the model's providers
Text
Images
Text

Capabilities

Supported operations and provider-stated features

VisionFunction callingStructured outputPrompt caching

Listings

 Mistral AIministral-3b-2512 · 2512Sources: GenAI Prices data, LiteLLM data, Mistral API data, Models.dev data262K$0.10cache read $0.01$0.10—
 Microsoft Azureazure_ai/ministral-3bSources: LiteLLM data, Models.dev data128K$0.04$0.04—
 OpenRouterministral-3bSource: GenAI Prices dataNot published by the provider$0.04$0.04—
 Vercel AI Gatewayvercel_ai_gateway/mistral/ministral-3bSource: LiteLLM data128K$0.04$0.04—
 NanoGPTInference by KitaniRegions: GLBmistralai/ministral-3b-2512 · 2512 · int4Source: NanoGPTNot published by the provider$0.0945cache read $0.0473$0.0945—
 Eden AIInference by Mistral AImistral/ministral-3b-2512 · 2512Source: Models.dev data131K$0.10cache read $0.01$0.10—
 Flowdotministral-3b-2512 · 2512Source: FlowDot data128K$0.10$0.10—
 Kilomistralai/ministral-3bSources: Kilo AI Gateway data, Models.dev data131K$0.10cache read $0.01$0.10$0.00
 Llmgatewayministral-3b-2512 · 2512Source: LLMGateway data131K$0.10$0.10—
 Nous Portalmistralai/ministral-3b-2512 · 2512Source: Nous Portal Inference Gateway data131K$0.10cache read $0.01$0.10—
Show all 26 listings

Showing 10 of 26: the maker's own listing first, then the cheapest per 1M input tokens from each provider.

Also sold by 302ai, Aimlapi, Cortecs AI, Llmgateway Providers, Lowrouter, Vercel.

4 listings without a price are hidden.

Benchmarks

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

General

Human preference

Math

AIME 2024Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim
AIME 2025Source: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Coding

Factuality

Science

GPQASource: LLM Stats data · Reported by the model's developer. The source relaying it did not verify it. claim

Multilingual

Reasoning

Other

Data credits: Data by LLM Stats · Epoch AI Benchmarking Hub, CC BY 4.0 (licence) · SnakeBench (Greg Kamradt / ARC Prize Foundation), MIT (licence) · Vectara Hallucination Leaderboard, Apache-2.0 (licence)

Also known as: azure_ai/ministral-3b, ministral-3b-2512, ministral-3b-latest, mistral/ministral-3b, mistral/ministral-3b-2512, mistral/ministral-3b-2512@eu, mistral/ministral-3b-latest, mistralai/ministral-3b, mistralai/ministral-3b-2512, vercel_ai_gateway/mistral/ministral-3b

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