← Model list
Ministral 3 14B
mistral·mistral/ministral-14b-instruct-2512-2·GA·Open weights·ministral series
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
At a glance
Reference price$0.20 / $0.20 per 1M
Cache read — · DigitalOcean
Lowest paid$0.10 / $0.40
NanoGPT Gateway · 2× spread
Context262,144
Output limit128,000
Capabilities
ReasoningTool useStructured output✓ Temperature✓ Attachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff—
Released / updated2025-12-02 / 2026-04-30
Quality & performanceArtificial Analysis · Intelligence Index v4.1
Intelligence11.2
Value64
Coding14.4
Agentic2.2
Output speed94 tok/s
TTFT0.84 s
Cost per task$0.1584
Value formulaIQ 11.2 ÷ min blended $0.175 = 64
Quality is independently evaluated by Artificial Analysis. Speed/latency are model-level medians.
Available at 2 providers2 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| NanoGPT mistralai/ministral-14b-instruct-2512 | Gateway | $0.10 | $0.40 | $0.05 | — | 262,144 | 32,768 | |
| DigitalOcean mistral-3-14B | Cloud | $0.20 | $0.20 | — | — | 262,144 | 128,000 |
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
1NanoGPT$34.00
2DigitalOcean$50.00
The cheapest paid channel is the only channel.
Related models
Ministral 3 14B Instructsame series$0.37 / $0.50Ministral 3 3B Reasoning 2512same series$1.04 / $0.548Ministral 3 8Bsame series$0.15 / $0.15Ministral 3Bcheaper alternative$0.10 / $0.10Lyria 3 Clip Previewcheaper alternative$0 / $0Qwen2.5 7B Instructcheaper alternative$0.072 / $0.144Granite 4.1 8Bcheaper alternative$0.05 / $0.10
Price historyone sample accumulated per data sync
Input listOutput listMin blended