Ministral 3 14B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Context
262,144
Max output
32,768
Input / 1M
$0.10
Output / 1M
$0.40
Providers
2
01Profile
Profile
Released
2025-12-02
Last updated
2025-12-02
Knowledge cutoff
—
Weights
Open
02Capabilities
Capabilities
Input
text · image
Output
text
Reasoning
No
Tool calling
No
Structured output
No
Attachments
Yes
Cache read
—
Cache write
—
03Pricing
Pricing across 1 providers
Per 1M tokens, USD. Sorted by input price. First-party row highlighted.
04History
Change history
8+ recent events since 2025-12-02
2026-07-27Addednvidiaoffering→ new
2026-05-03Removednvidiaofferingremoved→ new
2026-02-17Price cutnano-gptinput / 1M$1.00→ $0.10
2026-02-17Price cutnano-gptoutput / 1M$2.00→ $0.40
2026-02-17Contextnano-gptContext window131,072→ 262,144
2026-02-17Contextnano-gptMax output8,192→ 32,768
2025-12-27Addednano-gptoffering→ new
2025-12-10Addednvidiaoffering→ new