Last verified
ARCHIVE PRICERETIRED VISION128K CONTEXTTEXT + VISION

Pixtral 12B API Pricing

Pixtral 12B is retired; this archive preserves its listed API price while pointing new work to ministral-3-14b. Baseline token 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.

Archived Input - per 1M tokens
$0.15/M
Source Mistral retired archive
Archived Output - per 1M tokens
$0.15/M
Context 128K retired archive
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.

Archive calculator pre-loaded with Pixtral 12B rates. Tweak spend, output mix, or cache assumptions to compare this row against 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
CODING AGENT

Repo task iteration

$0.008/task
50,000 in - 5,000 out~12,048 units/$100
LONG DOC

Contract review

$0.027/doc
180,000 in - 2,000 out~3,663 units/$100
RAG

Knowledge base answer

$0.001/query
8,000 in - 1,000 out~76,923 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 406
Words 64
Tokens (estimated) 80 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
Pixtral 12B Current $0.15 $0.15 $0.15 agentic 92/8 128K General Mistral workloads
Mistral Large 3 $0.50 $1.50 $0.58 pricier 256K Frontier multimodal work
Mistral Medium 3.5 $1.50 $7.50 $1.98 pricier 256K General Mistral workloads
Mistral Small 4 $0.15 $0.60 $0.19 pricier 256K Low-cost chat and support
Codestral $0.30 $0.90 $0.35 pricier 256K Code generation and agents
Devstral 2 $0.40 $2.00 $0.53 pricier 256K Code generation and agents
Magistral Medium $2.00 $5.00 $2.24 pricier 128K Transparent reasoning
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 archived prices separated from current availability.

Q · 01 What is Pixtral 12B priced at? +
Pixtral 12B is shown here at $0.15/M input and $0.15/M output. For retired or deprecated rows, the price is preserved as an archive baseline.
Q · 02 Is Pixtral 12B still available? +
Pixtral 12B is retired in the current Mistral docs. Use ministral-3-14b for new production traffic when available.
Q · 03 Does Mistral list prompt caching for this model? +
No separate prompt-cache SKU is published for this row. The calculator therefore treats cache-hit input as the base input rate, $0.15/M, so the effective blend does not assume a hidden discount.
Q · 04 What does the effective price mean? +
The effective tile uses the site-wide agentic blend: 92% input tokens, 8% output tokens, and no cache discount unless a vendor lists one. For Pixtral 12B, that gives $0.15/M.
Q · 05 Where does the archive price come from? +
For active rows, the price comes from Mistral's current pricing or model card. For retired rows, AI//COST preserves the verified snapshot price and uses Mistral's current docs to verify deprecation, retirement, and replacement status.
Q · 06 Is there a batch discount? +
Mistral exposes batching in the API docs, but this archive row does not publish a separate per-model batch rate. The calculator keeps the baseline token prices visible and avoids inventing a discount.
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.