Mistral: Ministral 3 3B 2512

Public pricingIntelligence 79/100Medium memoryVisieToolgebruik

Mistral: Ministral 3 3B 2512 is een multimodaal-model voor beeld-taalbegrip. Het combineert multimodale invoerverwerking en beeldbegrip, een context van 131K tokens en een laag geprijsd-profiel voor betrouwbaar werk in vision-language understanding and content analysis.

Input

$0.10/1M

Output

$0.10/1M

Cached

$0.01/1M

Batch

$0.05/1M

Calculate your Ministral 3 3B 2512 bill.

Set your workload — see cost at your exact volume.

What would Ministral 3 3B 2512 cost you?

Adjust the workload to see your monthly bill.

1,00010,00050,000250,0001M10M

Technical specifications

Ministral 3 3B 2512 at a glance.

Memory

131,072

tokens

Max reply

32,768

tokens

Memory tier

Medium

a long report or a codebase file

Tokenizer

mistral

Released

Dec 2025

Training cutoff

Jun 2025

Availability

Public pricing

Status

active

What it can do

Capabilities & limits.

  • Understands images
  • Deep step-by-step thinking
  • Uses tools / calls functions
  • Strict JSON output
  • Streams replies
  • Fine-tunable on your data

When to pick Ministral 3 3B 2512

  • Screenshot analysis, image understanding, or document OCR.
  • Agentic workflows that call tools or APIs.
  • High-volume workloads where unit cost matters.
  • Multimodal pipelines mixing text + images.

When to look elsewhere

  • Very latency-sensitive, real-time apps where every millisecond counts.

Alternatives

Similar models to compare.

FAQ

Ministral 3 3B 2512 — the questions we see most.

Pricing, capabilities, alternatives — generated from the same data that powers the calculator above.

Get instant answers from our AI agent

At a typical workload of 50,000 conversations a month with 1,500-token prompts and 800-token replies, Ministral 3 3B 2512 costs roughly $12 per month. Input is $0.10 /1M tokens and output is $0.10 /1M tokens.
Ministral 3 3B 2512 has a 131,072-token context window (medium memory — a long report or a codebase file). That means you can fit about 24,576 words of input and history in a single call.
Beyond text generation, Ministral 3 3B 2512 supports understanding images, calling functions / tools, strict JSON output, fine-tuning on your own data. It streams replies by default.
Ministral 3 3B 2512 was released in December 2025, with training data cut off around June 2025.
Models in a similar class include Voxtral Small 24B 2507, Mistral Small 3.2 24B, Ministral 3 8B 2512. The "Similar models" section below this FAQ links into each.

Still unsure?

Compare Ministral 3 3B 2512 against 100+ other models.

Open the full wizard — pick a use case, set your usage, and see side-by-side monthly costs in under a minute.

Open the comparison wizard