LLM Pricing
ModelsLeaderboardsToolsProvidersReleasesArticles

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list

Ministral 3 3B

mistral·mistral/ministral-3-3b-instruct-2512·GA·Open weights·ministral series
Compact open vision-language model for edge deployment, instruction following, and tool use

Specs & pricing

Input / output per 1M tokens
Official price·Mistral
$0.10 / $0.10
Blended $0.10 · Cache read $0.01
Lowest paid·MistralFirst-party
$0.10 / $0.10
Blended $0.10 · 1× spread
Context
131,072
Output limit
131,072
Knowledge cutoff
—
Released / updated
2025-12-02 / 2025-12-02
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImagePDF
License
Apache-2.0
Weights
Hugging Face

Ministral 3 3B by mistral is offered by 3 providers on this page. Its official list price is $0.10 per 1M tokens. No paid channel is priced below the official list price.

Median output speed is 208 tokens per second, with 0.74s to the first token.

The context window is 131,072 tokens at the reference host, but hosts report different limits, from 131,072 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.

Quality & performanceArtificial Analysis · Intelligence Index v5

Intelligence—
Value—
Output speed208 tok/s
TTFT0.74 s

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

Available at 3 providers3 with public prices

  • ProviderInput / Output
  • MistralOfficialFirst-party
    ministral-3b-2512
    $0.10 / $0.10
    Cache read $0.01Context 131,072Output limit 131,072
  • Amazon BedrockCloud
    mistral.ministral-3-3b-instruct
    $0.10 / $0.10
    Context 256,000 ⚠Output limit 8,192
  • LowRouterGateway
    auto/mistralai/ministral-3b-2512
    $0.10 / $0.10
    Cache read $0.011Context 262,144 ⚠Output limit 262,144
ProviderTierInputOutputCache readCache writeContextOutput limitStatus
MistralOfficial
ministral-3b-2512
First-party$0.10$0.10$0.01—131,072131,072
Amazon Bedrock
mistral.ministral-3-3b-instruct
Cloud$0.10$0.10——256,000 ⚠8,192
LowRouter
auto/mistralai/ministral-3b-2512
Gateway$0.10$0.10$0.011—262,144 ⚠262,144

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$14.20
2LowRouter$14.86
3Amazon Bedrock$25.00
The cheapest paid channel is official.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.10$02026-09-122026-10-08
2026-10-08Input list $0.10Output list $0.10Min blended $0.10

Artificial Analysis evaluations20 items

GPQA Diamond35.8%
Humanity's Last Exam5.4%
HLE-Diamond5.1%
MMMU-Pro38.1%
CritPt0.0%
SciCode15.3%
LiveCodeBench24.7%
Terminal-Bench Hard0.0%
Terminal-Bench 2.10.0%
Terminal-Bench 4.00.0%
AIME 202522.0%
τ²-Bench Telecom24.9%
τ³-Bench Banking4.7%
AutomationBench-AA0.7%
AA-Briefcase0
GDPval-AA37
GDP.pdf0.0%
AA-LCR17.0%
MLCR-AA0.0%
IFBench26.8%

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—Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0Ministral 3 14Bsame lab$0.20 / $0.20Ministral 3 8Bsame lab$0.15 / $0.15
Data partly from models.dev (MIT) · Mistral official docs ↗