Last verified
ARCHIVE PRICERETIRED MODEL32K CONTEXTOPEN WEIGHTS

Mistral 7B API Pricing

Mistral 7B is retired; this archive preserves its API price and replacement guidance. Baseline rates are $0.25/M input and $0.25/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
$0.25/M
Source Mistral archive
Archived Output - per 1M tokens
$0.25/M
Context 32K archive
Cache N/A
$0.25/M
Cache no separate SKU not listed
Effective - agentic blend
$0.25/M
92/8 split - 82% cache
§ 01 / TERMINAL

Run the numbers.

Archive calculator pre-loaded with Mistral 7B 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
—
§ 02 / SCENARIOS

Real-world presets.

CHATBOT

Support assistant

$0.001/turn
2,000 in - 500 out~166,666 units/$100
CODE

Code completion

$0.004/task
12,000 in - 2,000 out~28,571 units/$100
EDGE RAG

Compact retrieval

$0.002/query
8,000 in - 1,000 out~43,478 units/$100
BULK

Batch classification

$0.000/item
1,000 in - 100 out~333,333 units/$100
§ 03 / TAPE

Price history.

Archived at $0.25/M input and $0.25/M output.

Input · $0.25/M
Output · $0.25/M
Cached · $0.25/M
SEP 27 Launch price $0.25/M input and $0.25/M outputMAY 18 Archive verification kept $0.25/M and $0.25/M
§ 04 / TOKENIZER

Paste text. See tokens. See cost.

Estimate · mistral-tokenizer-estimate · ≈3.85 chars/token Auto-counts as you type

This is a chars-per-token approximation, not a real tokenizer. Actual tokens vary by language, code density, and tool-call overhead — counts are typically ±10–20% off for English prose, more for code or non-Latin scripts. For exact billing, use the vendor's official tokenizer.

Characters —
Words —
Tokens (estimated) —
Cost as input · uncached —
Cost as output · uncached —
Cost as cached input —
§ 05 / SHELF

Up against the shelf.

All models →
Model Input /M Output /M Effective blended Context Best for
Mistral 7B Current $0.25 $0.25 $0.25 agentic 92/8 32K General Mistral workloads
Ministral 3 14B $0.20 $0.20 $0.20 cheaper 128K Edge inference and compact agents
Ministral 3 8B $0.15 $0.15 $0.15 cheaper 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 cheaper 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 Mistral 7B priced at? +
Mistral 7B is shown at $0.25/M input and $0.25/M output. For retired rows, this is an archive baseline, not a current availability claim.
Q · 02 Is Mistral 7B still available? +
Mistral 7B is marked as retired in the current Mistral docs. New production work should normally move to ministral-3-8b.
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 $0.25/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 Mistral 7B, that is $0.25/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 May 18, 2026
Methodology Report a correction More by Y.V.