LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Ministral 3 14B

mistral·mistral/ministral-3-14b-instruct-2512·BETA·Open weights·ministral series
Open vision-language model for efficient local deployment, instruction following, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Mistral
$0.20 / $0.20
Blended $0.20 · Cache read $0.02
Lowest paid·MistralFirst-party
$0.20 / $0.20
Blended $0.20 · 1.9× spread
Context
262,144
Output limit
262,144
Knowledge cutoff
—
Released / updated
2025-12-02 / 2025-12-02
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImagePDF
License
Apache-2.0
Weights
Hugging Face

Ministral 3 14B by mistral is offered by 7 providers on this page. Its official list price is $0.20 per 1M tokens. No paid channel is priced below the official list price. Prices vary about 1.9× across the providers that host it.

Median output speed is 94 tokens per second, with 0.94s to the first token.

The context window is 262,144 tokens at the reference host, but hosts report different limits, from 100,000 to 262,144, so the usable window depends on the provider you pick. It supports tool use and structured output. Accepted input modalities are Text, Image, and PDF. The weights are open, so it can also be self-hosted or served through a gateway of your choice. Providers report the capability flags inconsistently, so verify a specific feature against the host you plan to use.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed94 tok/s
TTFT0.94 s

Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.

Available at 7 providers7 with public prices

  • ProviderInput / Output
  • MistralOfficialFirst-party
    ministral-14b-2512
    $0.20 / $0.20
    Cache read $0.02Context 262,144Output limit 262,144
  • DigitalOceanCloud
    mistral-3-14B
    $0.20 / $0.20
    Cache read $0.04Context 262,144Output limit 128,000
  • NanoGPTGateway
    mistralai/ministral-14b-instruct-2512
    $0.20 / $0.20
    Cache read $0.02Context 262,144Output limit 32,768
  • Amazon BedrockCloud
    mistral.ministral-3-14b-instruct
    $0.20 / $0.20
    Context 128,000 ⚠Output limit 4,096
  • LowRouterGateway
    auto/mistralai/ministral-14b-2512
    $0.21 / $0.21
    Cache read $0.021Context 262,144Output limit 262,144
  • Eden AIGateway
    infomaniak/mistralai/Ministral-3-14B-Instruct-2512
    $0.33 / $0.44
    Context 100,000 ⚠Output limit 100,000
  • InfomaniakCloud
    mistralai/Ministral-3-14B-Instruct-2512
    $0.37 / $0.50
    Context 100,000 ⚠Output limit 25,600beta
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
MistralOfficial
ministral-14b-2512
First-party$0.20$0.20$0.02—262,144262,144
DigitalOcean
mistral-3-14B
Cloud$0.20$0.20$0.04—262,144128,000
NanoGPT
mistralai/ministral-14b-instruct-2512
Gateway$0.20$0.20$0.02—262,14432,768
Amazon Bedrock
mistral.ministral-3-14b-instruct
Cloud$0.20$0.20——128,000 ⚠4,096
LowRouter
auto/mistralai/ministral-14b-2512
Gateway$0.21$0.21$0.021—262,144262,144
Eden AI
infomaniak/mistralai/Ministral-3-14B-Instruct-2512
Gateway$0.33$0.44——100,000 ⚠100,000
Infomaniak
mistralai/Ministral-3-14B-Instruct-2512
Cloud$0.37$0.50——100,000 ⚠25,600beta

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

Common scenarios
1Mistral · Official$28.40
2NanoGPT$28.40
3LowRouter$29.70
4DigitalOcean$30.80
5Amazon Bedrock$50.00
6Eden AI$87.94
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.40$02026-08-082026-11-14
2026-11-14Input list $0.20Output list $0.20Min blended $0.20

Artificial Analysis evaluations20 items

GPQA Diamond57.2%
Humanity's Last Exam4.6%
HLE-Diamond4.4%
MMMU-Pro49.8%
CritPt0.0%
SciCode23.8%
LiveCodeBench35.1%
Terminal-Bench Hard4.5%
Terminal-Bench 2.19.7%
Terminal-Bench 4.00.0%
AIME 202530.0%
τ²-Bench Telecom27.2%
τ³-Bench Banking6.6%
AutomationBench-AA0.5%
AA-Briefcase132
GDPval-AA255
GDP.pdf1.2%
AA-LCR26.3%
MLCR-AA2.2%
IFBench32.0%

Individual evaluations run by Artificial Analysis, on the same reasoning tier as the intelligence score above. Each benchmark has its own task set and scale (percent correct, points or an index), so rows are not comparable with one another.

Related models

Ministral 3 3B Reasoning 2512same series—Ministral 3 14B Reasoning 2512same series—Ministral 3 14B 2512same series—Nova Litecheaper alternative$0.06 / $0.24Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0Ministral 3 3Bcheaper alternative$0.10 / $0.10
Data partly from models.dev (MIT) · Mistral official docs ↗