Skip to content
Toolsummary LLM price ledger

Pixtral 12 B2409 vs Ministral 3 14 B Instruct 2512: cost comparison

Prices updated 2026-11-18 · computed from live provider data

Short answer: Ministral 3 14 B Instruct 2512 is cheaper on a 3:1 input/output blend — $0.200 per million tokens versus $0.200, a 0% difference. Ministral 3 14 B Instruct 2512 offers the larger context window at 262,144 tokens, against 128,000 for Pixtral 12 B2409.

Head to head

Pixtral 12 B2409Ministral 3 14 B Instruct 2512
Input, per 1M tokens$0.200$0.200
Output, per 1M tokens$0.200$0.200
Blended 3:1, per 1M$0.200$0.200
Context window128,000262,144
Vendorscalewaytogether_ai

Monthly cost at real volumes

Workload (input / output)Pixtral 12 B2409Ministral 3 14 B Instruct 2512
1M in / 250K out$0.250$0.250
10M in / 2.5M out$2.50$2.50
100M in / 25M out$25.00$25.00

Which should you pick?

Pick Ministral 3 14 B Instruct 2512 when you need the longer context window (262,144 vs 128,000 tokens). Pick Ministral 3 14 B Instruct 2512 when price per token dominates your workload — high-volume classification, extraction, or batch summarisation.

Related