Skip to content
CostPerPrompt

Ministral 3 8B 2512 (batch) API Pricing

Mistral · context window 262K · prices updated 2026-09-15

Input per 1M tokens
$0.075
Output per 1M tokens
$0.075
Cached input per 1M
$0.0075
90% cheaper than fresh input

Where Ministral 3 8B 2512 (batch) sits on price

At $0.075 per million output tokens, Ministral 3 8B 2512 (batch) is a budget tier model — 27.7× cheaper than the median output price of $2.08, which puts it in the cheapest 10% of everything we track. It sits 2th cheapest of the 25 Mistral models we track. Output is only 1.0× the input price, an unusually flat spread: long prompts hurt about as much as long answers, so prompt size is where the savings are.

Output tokens per $1
13,333,333
One full context fill
$0.0197
Cheaper than
100% of tracked models

Cached input is 90% cheaper. On an input-heavy workload you need roughly a 28% cache-hit rate to take 25% off the input line — reachable for chatbots and agents that resend the same system prompt and history.

What real workloads cost on Ministral 3 8B 2512 (batch)

These three workloads are the ones teams actually run on a budget-priced model — a $0.075/1M model is not bought for the same job as one ten times the price.

Workload Per request Per month
High-volume classification — 200K requests/day (400 in / 20 out) Short output, huge volume: the input price dominates the bill. $0 $189
Small app — 1K requests/day (500 in / 150 out) The baseline most side projects actually run at. $0 $1.46
Document pipeline — 10K docs/day (3K in / 500 out) Batch-friendly: no user waiting, so a ~50% batch discount usually applies. $0.0003 $78.75

Model your exact traffic in the API cost calculator — it preloads Ministral 3 8B 2512 (batch) with caching and batch options.

Ministral 3 8B 2512 (batch) price history

Mistral last cut Ministral 3 8B 2512 (batch)'s output price on Sep 10, 2026 (-50% per output token), from $0.15/$0.15 to $0.075/$0.075 per 1M in/out. That is the only repricing in the 18 days we have tracked it — worth knowing before you hard-code today's rate into a budget.

Date Input /1M Output /1M Output change
Aug 28, 2026 (tracking began) $0.15 $0.15
Sep 10, 2026 $0.075 $0.075 -50%

Change-points from our daily price snapshots (tracking since Aug 28, 2026; intraday moves between snapshots are not captured).

Ministral 3 8B 2512 (batch) vs Llama 3.1 8B Instruct

The closest-priced alternative from another vendor is Llama 3.1 8B Instruct (Meta) — 7% more expensive on output, with $0.025 less per million input tokens. When two models land this close on price, the decision is quality on your own workload, not the price sheet: run 50 real requests through both and compare.

See Llama 3.1 8B Instruct pricing →

Cheaper alternatives

More Mistral models

Frequently asked questions

How much does the Ministral 3 8B 2512 (batch) API cost?

Ministral 3 8B 2512 (batch) costs $0.075 per million input tokens and $0.075 per million output tokens, with cached input at $0.0075 per million (90% cheaper). That works out to roughly 13,333,333 output tokens per dollar.

What does the high-volume classification workload cost on Ministral 3 8B 2512 (batch)?

High-volume classification — 200K requests/day (400 in / 20 out) costs about $0 per request and $189 per month on Ministral 3 8B 2512 (batch). Short output, huge volume: the input price dominates the bill.

What does it cost to fill Ministral 3 8B 2512 (batch)'s 262K context window?

Sending 262K of input in a single request costs $0.0197 at $0.075 per million tokens — before any output. With prompt caching that same fill drops to about $0.002 on repeat requests. This is why large context windows are cheap to advertise and expensive to actually use.

Is Ministral 3 8B 2512 (batch) worth the price?

Ministral 3 8B 2512 (batch) is in the cheapest end of the market — cheaper than 100% of the models we track. At this price the question is not cost but capability: it is a good fit for classification, extraction, routing and bulk summarisation, and a poor fit for multi-step reasoning where a wrong answer costs more than the tokens saved.