Skip to content
ModelCap

Ministral 3 14B 2512

Official publisher releaseOpen weights

Mistral AI

Ministral 3 14B 2512 is a language model from Mistral AI. It does not hold a position on ModelCap's current board yet; it is placed automatically once its model card or a public benchmark compares it with ranked models. It is listed at $0.20 per million input tokens and $0.20 per million output tokens from one provider. It reads up to 262K tokens of context, and its weights are openly downloadable.

Figures as of 6 Nov 2026, 20:32 UTC · download the public dataset · methodology

ModelCap Index · Current board
—
Index position pending
Market Gravity
20.0Decreased by 0.2
Secondary market signal
Input
$0.20
per 1M tokens
Output
$0.20
per 1M tokens
Context
262K
tokens
Providers
1
2 endpoints

Providers

Uptime measured over the last 30 minutes
ProviderInputOutputContextQuantUptime
MistralzdrCheapest$0.20$0.20262K—100.0%
Mistraleu$0.22$0.22262K—100.0%

ModelCap Index · Current board

Methodology
—
Index position pending
Technical details
Public rank basis
Index position pending (abstained)
Evidence label
Index position pending · insufficient shared rows
Index support
0.0% · not applicable
Identity binding
Exact catalogue product · mistralai/mistralai/ministral-14b-2512/fp8 · aggregates disclosed benchmark configurations · endpoint configuration not claimed · artifact metadata mistralai/Ministral-3-14B-Instruct-2512@29439f81c2be264d8d393273f99e7db9c0961120 (not the evaluation revision)
Index observations used
0
Architecture fallback
abstained · 0% coverage · 0 anchors
Bayesian Evidence Score · measured evidence input only

BES normalizes admitted public benchmark evidence for measured Index rows. Its legacy score and observables prior do not define the public language rank.

Observed capability
—
Evidence status
No admitted measured evidence
General preference
—
Coding
—
Agents & tools
—
Reasoning
—
Evidence breadth
0%
Evidence coverage
0%
Market and catalogue signals · secondary, never the language Index rank
Usage (OpenRouter popularity)
8.3
Liquidity (providers × uptime)
24.3
Open reach (HF downloads)
53.6
Surface (context / tools / modalities)
65.3
Freshness
27.5
  • · OpenRouter popularity #209
  • · 1 live provider
  • · HF 30d downloads 163392
  • · Catalogue: context 262144, tools, modalities Text/Image
  • · First seen 2025-12-02

These adoption and deployment observations remain context only. They do not change this model's ModelCap Index score or rank.

The bounded 0–100 capability score blends each source’s competitive placement with its published achievement, then combines capability families. Evidence breadth adds a modest uncertainty adjustment; price and popularity are not part of benchmark-led rank.

Experimental capability estimate

Estimate policy
34.9
20.9–49.0 uncertainty interval
Excluded from rank
Confidence
78%
Training support
221 models · 129 lineages
Out-of-domain check
in domain
Feature coverage
100%
Lineage-held-out error
8.3 MAE

Experimental estimate. This layer predicts from admitted evidence and safe metadata only. It never enters ModelCap Score or rank.

Deployment readiness

Metadata index
74.0
partial · 80% metadata coverage
Not capability
Artifact reproducibility
100.0
Access & legal clarity
100.0
Deployability
80.0
Evaluation provenance
0.0

Not yet published: admitted benchmark results, results across several capability areas, results from more than one source, a confident match to its benchmark entries, pinned evaluation dataset versions.

A metadata completeness and deployability index—not a safety certification, quality grade, or production-readiness claim.

Market activity

Venue coverage
Market Gravity
20.0
OpenRouter weekly popularity
#209 of 339

Market Gravity uses OpenRouter’s full-catalogue popularity order. Sparse Vercel top-ten observations appear only when published and do not affect the score.

Arena preference

No matched Arena rating

This model is visible because it is available in the live catalogue, but it has no trustworthy community result yet. ModelCap does not infer a quality score from price, features, or market activity.

Market Gravity breakdown

Usage55%
8.3

OpenRouter weekly popularity across the full model catalogue.

Liquidity25%
24.3

Independent providers versus the model's open or closed cohort, weighted by uptime.

Open reach15%
53.6

Hugging Face 30-day downloads for open models; neutral for closed models.

Freshness5%
27.5

Time since first public availability, on a six-month half-life.

Specification

Model ID
mistralai/ministral-14b-2512
Context window
262K tokens
Declared output cap
210K tokens

OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. OpenRouter metadata

Inputs
Text, Image
Outputs
Text
Tokenizer
Mistral
Cached input tokens
$0.02 / 1M
First seen on OpenRouter
2 Dec 2025

Capabilities

  • Not supported: Reasoning
  • Supported: Tool use
  • Supported: Structured output
  • Supported: Response format
  • Not supported: Moderated

Weights & access

Open weights. Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI.

Access
Open weights
Licence
apache-2.0
Pinned revision
29439f81c2be
Parameters
13.9B
Architecture
Mistral3ForConditionalGeneration
Model type
mistral3
Hugging Face downloads (30d)
163K
Downloads (all time)
2.5M
Likes
351
Repository updated
15 Jul 2026, 12:20 UTC

Ministral 3 14B 2512: common questions

How does Ministral 3 14B 2512 rank among AI models?

Ministral 3 14B 2512 has no public ModelCap Index position as of 6 November 2026: the snapshot lacks enough matched benchmark evidence, or the identity match is unresolved. Its catalogue facts (price, context, providers) are shown without a rank.

How much does Ministral 3 14B 2512 cost per 1M tokens?

Ministral 3 14B 2512 is listed at $0.20 per 1M input tokens and $0.20 per 1M output tokens as of 6 November 2026. Prices come from the OpenRouter catalogue and re-observe on every refresh. For 1,000 requests using 2,000 input and 500 output tokens each, the listed rates imply $0.50 total (2M input + 0.5M output). This excludes caching, batch discounts, prompt-length tiers, tool charges and retries; verify the chosen endpoint's rate and limits before budgeting.

What is the context window of Ministral 3 14B 2512?

Ministral 3 14B 2512 has a published context window of 262K tokens (262,144). The snapshot lists a 209,715 token catalogue-declared route output cap. OpenRouter catalogue or provider-endpoint declaration. Limits can vary by provider and prompt length; a model-wide maximum has not been independently verified. The providers table lists each endpoint's context limit.

Is Ministral 3 14B 2512 open-weight?

Open weights (apache-2.0). Downloadable weights are published under an OSI or free-culture license in the current repository metadata. This describes weight availability, not whether the full training stack qualifies as Open Source AI. The repository is mistralai/Ministral-3-14B-Instruct-2512 on Hugging Face.

Which API providers serve Ministral 3 14B 2512?

One provider serves Ministral 3 14B 2512 through OpenRouter as of 6 November 2026: Mistral. Each provider's price, context limit, quantization and measured uptime are in the providers table above.

When was Ministral 3 14B 2512 released?

Ministral 3 14B 2512 first appeared in the catalogue on 2 Dec 2025. It is the current version in its family. Rank and price movements since then are recorded on the site's changes feed.