LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 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

Ministral 3 3B by mistral is currently listed from a single provider. Its reference price is $0.10 per 1M tokens.

Artificial Analysis rates it 4.8 on the Intelligence Index, with 4.8 for coding and 0.8 for agentic tasks. Against its lowest blended price of $0.10 per 1M, that is roughly 48 index points per dollar, which is the value ratio the leaderboards rank on. Median output speed is 209 tokens per second, with 0.66s to the first token. Running one task of the Artificial Analysis suite costs about $0.0423, which reflects how many tokens its reasoning consumes rather than the unit price alone.

The context window is 256,000 tokens, with an output limit of 8,192 tokens. It supports tool use and structured output. Accepted input modalities are Text and Image. The weights are open, so it can also be self-hosted or served through a gateway of your choice.

Specs & pricing

Input / output per 1M tokens
Reference price·Amazon Bedrock
$0.10 / $0.10
Blended $0.10 · Cache read —
Lowest paid·Amazon BedrockCloud
$0.10 / $0.10
Blended $0.10
Context
256,000
Output limit
8,192
Knowledge cutoff
—
Released / updated
2025-12-02 / 2025-12-02
Capabilities
Reasoning✓ Tool use✓ Structured output✓ Temperature✓ Attachments
Modalities
TextImage
License
Apache-2.0
Weights
Hugging Face

Quality & performanceArtificial Analysis · Intelligence Index v4.3

Intelligence4.8
Value48
Coding4.8
Agentic0.8
Output speed209 tok/s
TTFT0.66 s
Cost per task$0.0423
Value formulaIQ 4.8 ÷ min blended $0.100 = 48

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

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
Amazon Bedrock
mistral.ministral-3-3b-instruct
Cloud$0.10$0.10——256,0008,192

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

1Amazon Bedrock$25.00
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input list $0.10Output list $0.10Min blended $0.10

Price history accumulates from each data sync; currently only 1 sample(s) (2026-09-12). Each future sync adds a point, and once accumulated a line is drawn here.

Artificial Analysis evaluations12 items

GPQA Diamond35.8%
Humanity's Last Exam5.4%
MMLU-Pro52.4%
SciCode15.3%
LiveCodeBench24.7%
Terminal-Bench Hard0.0%
Terminal-Bench 2.10.0%
AIME 202522.0%
τ²-Bench Telecom24.9%
τ³-Bench Banking4.7%
AA-LCR17.0%
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 harness, so rows are not comparable with one another. The Intelligence Index above draws on a different, newer set of evaluations.

Related models

Ministral 3 3B Reasoning 2512same series$1.04 / $0.548Ministral 3 14B Reasoning 2512same series$2.50 / $1.70Ministral 8Bsame series$0.15 / $0.15Ministral 3Bcheaper alternative$0.04 / $0.04Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0
Data partly from models.dev (MIT) · Amazon Bedrock official docs ↗