chooseaimodel
← All models
Flashfastest and cheapest, lighter reasoningOpen Weights

Ministral 3 8B 2512 (batch) Pricing

Mistral AI · mistralai-ministral-8b-2512-batch

ShareXFacebookLinkedIn
Input / 1M tokens
$0.075
Output / 1M tokens
$0.075
Context window
262,144 tokens
350 pages of text
Max output
209,715 tokens

What it costs in practice

Estimate your own workloadOpens the calculator with Ministral 3 8B 2512 (batch) preloaded — adjust volume and token counts there.

Price history

List price per 1M tokens since we started tracking in Aug 2026. Each step marks a price change — hover a point for the exact date and rate.

What it excels at

Efficient for high-volume inference on long-context tasks with low per-token cost and open-weight deployment flexibility.

The business tradeoff

8B scale limits depth on complex multi-step reasoning and instruction following compared with larger models in the same family.

Cheaper from Mistral AI

Same tier from other providers

Head-to-head

Vendor list rates, as of Sep 10, 2026 · source: openrouter · per-request examples assume 1,200 input + 400 output tokens.