Last verified
ARCHIVE PRICERETIRED EDGE128K CONTEXTTEXT MODEL

Ministral 3B API Pricing

Ministral 3B is retired; this archive preserves its API price and replacement guidance. Baseline rates are $0.04/M input and $0.04/M output; no separate prompt-cache price is published for this row. Pulled from official Mistral sources and the project pricing snapshot.

Archived Input - per 1M tokens
$0.04/M
Source Mistral archive
Archived Output - per 1M tokens
$0.04/M
Context 128K archive
Cache N/A
$0.04/M
Cache no separate SKU not listed
Effective - agentic blend
$0.04/M
92/8 split - no cache
§ 01 / TERMINAL

Ministral 3B API cost calculator.

Archive calculator pre-loaded with Ministral 3B rates. Tweak spend, output mix, or cache assumptions to compare it with current Mistral replacements.

$ /mo
Workload split
Tokens you can process
—
Words equivalent (English)
—
Effective rate
—
Open full calculator (all models · share URL · CSV) →
§ 02 / SCENARIOS

Ministral 3B cost on real workloads.

CHATBOT

Support assistant

$0.0001/turn
2,000 in - 500 out~1,000,000 units/$100
CODE

Code completion

$0.00056/task
12,000 in - 2,000 out~178,571 units/$100
EDGE RAG

Compact retrieval

$0.00036/query
8,000 in - 1,000 out~277,777 units/$100
BULK

Batch classification

$0.00004/item
1,000 in - 100 out~many units/$100
§ 03 / TOKENIZER

Ministral 3B token counter and cost.

What's a token →
Calibrated · measured on the vendor's tokenizer · 2026-06-10 Auto-counts as you type

Counts use a chars-per-token calibration measured on the vendor's own published tokenizer (mistralai/Mistral-Nemo-Instruct-2407, 2026-06-10). English prose is typically within a few percent; code and non-Latin scripts tokenize heavier. For billing-exact counts use the vendor's count-tokens API.

Characters 411
Words 65
Tokens (estimated) 81 tokens
Cost as input · uncached $0.000003 USD
Cost as output · uncached $0.000003 USD
§ 04 / SHELF

Ministral 3B vs similar models.

All models →
Model Input /M Output /M Effective blended Context Best for
Ministral 3B Current $0.04 $0.04 $0.04 agentic 92/8 128K Edge inference and compact agents
Ministral 3 14B $0.20 cache $0.02 $0.20 $0.0642 +61% 128K Edge inference and compact agents
Ministral 3 8B $0.15 cache $0.015 $0.15 $0.0482 +20% 128K Edge inference and compact agents
Ministral 3 3B $0.10 cache $0.01 $0.10 $0.0321 −20% 128K Edge inference and compact agents
Mistral Small 4 $0.15 cache $0.015 $0.60 $0.0842 +2.1× 256K Low-cost chat and support
Codestral $0.30 cache $0.03 $0.90 $0.144 +3.6× documented elsewhere — not on pricing page Coding and code agents
Mistral Large 3 $0.50 cache $0.05 $1.50 $0.241 +6.0× documented elsewhere — not on pricing page General Mistral workloads
DeepSeek V4.1 Flash $0.30 cache $0.006 $1.20 $0.15 +3.8× 1M Budget coding and bulk reasoning

Ministral 3B API pricing FAQ.

Practical pricing questions, with archive status separated from current pricing.

Q · 01 What is Ministral 3B priced at? +
Ministral 3B is shown at $0.04/M input and $0.04/M output. For retired rows, this is an archive baseline, not a current availability claim.
Q · 02 Is Ministral 3B still available? +
Ministral 3B is marked as retired in the current Mistral docs. New production work should normally move to ministral-3-3b.
Q · 03 Does this model have prompt-cache pricing? +
Mistral does not publish a separate cache-read SKU for this row. The calculator therefore sets cached input to $0.04/M, the same as normal input, and does not invent a discount.
Q · 04 How is the effective price calculated? +
AI//COST uses the same agentic blend everywhere: 92% input, 8% output, and only published cache discounts. For Ministral 3B, that is $0.04/M.
Q · 05 Why keep an archive page? +
Archive pages are useful for invoice checks, migration planning, and comparing how model pricing compressed over time. They are clearly labeled so retired API rows do not look like current recommendations.
Q · 06 Are there regional surcharges? +
The Mistral public pricing page is denominated in USD and EUR. This page stores the USD baseline; currency conversion and localized calculator variants are handled elsewhere on AI//COST.
Y
Reviewed by Yaroslav Vikhariev Founder · AI//COST · Prices checked by hand against docs.mistral.ai · Last verified May 18, 2026
Methodology Report a correction More by Y.V.