Last verified
EDGE MID TIER128K CONTEXTTEXT + VISIONOPEN WEIGHTS

Ministral 3 8B API Pricing

Ministral 3 8B is Mistral's current edge mid-tier, with live pricing verified from the official pricing page. Baseline rates are $0.15/M input and $0.15/M output; no separate prompt-cache price is published for this row. Pulled from official Mistral sources and the project pricing snapshot.

Input - per 1M tokens
$0.15/M
Source Mistral flat
Output - per 1M tokens
$0.15/M
Context 128K flat
Cache N/A
$0.15/M
Cache no separate SKU not listed
Effective - agentic blend
$0.15/M
92/8 split - 82% cache
§ 01 / TERMINAL

Run the numbers.

Live calculator pre-loaded with Ministral 3 8B rates. Tweak spend, output mix, or cache assumptions to compare it with current Mistral replacements.

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

Real-world presets.

CHATBOT

Support assistant

$0.000/turn
2,000 in - 500 out~250,000 units/$100
CODE

Code completion

$0.002/task
12,000 in - 2,000 out~47,619 units/$100
EDGE RAG

Compact retrieval

$0.001/query
8,000 in - 1,000 out~76,923 units/$100
BULK

Batch classification

$0.000/item
1,000 in - 100 out~500,000 units/$100
§ 03 / TOKENIZER

Paste text. See tokens. See cost.

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 417
Words 67
Tokens (estimated) 82 tokens
Cost as input · uncached $0.000012 USD
Cost as output · uncached $0.000012 USD
Cost as cached input $0.000012 USD
§ 04 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Ministral 3 8B Current $0.15 $0.15 $0.15 agentic 92/8 128K Edge inference and compact agents
Ministral 3 14B $0.20 $0.20 $0.20 pricier 128K Edge inference and compact agents
Ministral 3 8B Current $0.15 $0.15 $0.15 agentic 92/8 128K Edge inference and compact agents
Ministral 3 3B $0.10 $0.10 $0.10 cheaper 128K Edge inference and compact agents
Mistral Small 4 $0.15 $0.60 $0.19 pricier 128K Low-cost chat and support
Codestral $0.30 $0.90 $0.35 pricier 128K Coding and code agents
Mistral Large 3 $0.50 $1.50 $0.58 pricier 128K General Mistral workloads
DeepSeek V4 Flash $0.14 cache $0.00 $0.28 $0.05 cheaper 1M Budget coding and bulk reasoning

Frequently asked.

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

Q · 01 What is Ministral 3 8B priced at? +
Ministral 3 8B is shown at $0.15/M input and $0.15/M output. This rate is the live baseline used in the calculator.
Q · 02 Is Ministral 3 8B still available? +
Ministral 3 8B is active in the current Mistral lineup, with pricing checked against the vendor pricing page on 2026-05-18.
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 $0.15/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 3 8B, that is $0.15/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 - Pricing pulled daily from mistral.ai - Last verified July 11, 2026
Methodology Report a correction More by Y.V.