prices synced 2026-07-28

Ministral 3 14B 2512

Mistral · Multimodal · Released Dec 2025

Compare

A 14-billion parameter language model from Mistral offering frontier-level performance in a compact form factor.

Strengths
Balances reasoning and generation quality with efficient inference across a wide range of tasks.
Best for
Applications requiring strong general-purpose capabilities where inference efficiency and latency matter.
Limitations
Smaller models may struggle with complex multi-step reasoning, very long-context summarization, or specialized domains requiring extensive training data.

Input / 1M

$0.2

Output / 1M

$0.2

Cached input / 1M

$0.02

Context window

262K

Price history

Price per 1M tokens over timeOutput $0.2; Input $0.2 as of Jun 2026.$0$0.05$0.1$0.15$0.2Output on 11 Jun 2026: $0.2Out $0.2Input on 11 Jun 2026: $0.2In $0.2Jun 2026

Snapshots

Effective Input Output Cached in Note Source
11 Jun 2026 $0.2 $0.2 $0.02 Imported from OpenRouter openrouter.ai

More from Mistral

Report a problem