LLM Pricing
PricingLeaderboardsToolsProvidersReleasesGuides

© 2026 LLM Pricing

About
·Contact
·Privacy
·RSS
← Model list
mi

ministral-3b-2512

misc·misc/ministral-3b-2512·GA·Closed
Ministral 3 3B is a compact, efficient multimodal model with strong language, vision capabilities, and ideal for custom fine-tuning.

Specs & pricing

Input / output per 1M tokens
Reference price·Cortecs
$0.12 / $0.12
Blended $0.12 · Cache read $0.012
Lowest paid·CortecsGateway
$0.12 / $0.12
Blended $0.12
Context
256,000
Output limit
256,000
Knowledge cutoff
—
Released / updated
2025-12-03 / 2025-12-03
Capabilities
Reasoning✓ Tool use✓ Structured outputTemperature✓ Attachments
Modalities
TextImage

Available at 1 providers1 with public prices

ProviderTierInputOutputCache readCache writeContextOutput limitStatus
CortecsGateway$0.12$0.12$0.012—256,000256,000

Sorted by blended price (input×0.75 + output×0.25) asc. The official channel always shows regardless of rank. Whether a gateway's low price is actually usable can't be verified.

Your usage cost

1Cortecs$17.43
The cheapest paid channel is the only channel.

Price historyone sample accumulated per data sync

Input listOutput listMin blended
$0.12$02026-08-082026-09-152026-08-08 · Input list $0.112026-08-09 · Input list $0.112026-08-10 · Input list $0.112026-08-11 · Input list $0.112026-08-12 · Input list $0.112026-08-13 · Input list $0.112026-09-15 · Input list $0.122026-08-08 · Output list $0.112026-08-09 · Output list $0.112026-08-10 · Output list $0.112026-08-11 · Output list $0.112026-08-12 · Output list $0.112026-08-13 · Output list $0.112026-09-15 · Output list $0.122026-08-08 · Min blended $0.112026-08-09 · Min blended $0.112026-08-10 · Min blended $0.112026-08-11 · Min blended $0.112026-08-12 · Min blended $0.112026-08-13 · Min blended $0.112026-09-15 · Min blended $0.12

Related models

Ministral 3Bcheaper alternative$0.04 / $0.04Command R7Bcheaper alternative$0.038 / $0.15inSchematron V2 Turbocheaper alternative$0.03 / $0.15Lyria 3 Clip Previewcheaper alternative$0 / $0
Data partly from models.dev (MIT) · Cortecs official docs ↗