← Model list
Ministral 3B
mistral·mistral/ministral-3b-2512·GA·Open weights·ministral series
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
At a glance
Reference price$0.10 / $0.10 per 1M
Cache read — · DevPass (LLM Gateway)
Lowest paid$0.04 / $0.04
Azure Cognitive Services First-party · 2.5× spread
Context131,072
⚠ Providers report 128,000–131,072; the table below is authoritative
Output limit8,192
Capabilities
ReasoningTool useStructured output✓ TemperatureAttachments
⚠ Providers report capability flags inconsistently
Modalities
TextImage
Knowledge cutoff2024-03
Released / updated2024-10-22 / 2025-12-04
Quality & performance
Artificial Analysis doesn't cover this model (267 of 2059 have data). Quality data comes from independent evals covering widely used models.
Available at 4 providers4 with public prices
| Provider | Tier | Input | Output | Cache read | Cache write | Context | Output limit | Status |
|---|---|---|---|---|---|---|---|---|
| Azure Cognitive Services ministral-3b | First-party | $0.04 | $0.04 | — | — | 128,000 ⚠ | 8,192 | |
| Azure ministral-3b | First-party | $0.04 | $0.04 | — | — | 128,000 ⚠ | 8,192 | |
| NanoGPT | Gateway | $0.10 | $0.10 | $0.05 | — | 131,072 | 32,768 | |
| DevPass (LLM Gateway) | Gateway | $0.10 | $0.10 | — | — | 131,072 | 8,192 |
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
1Azure Cognitive Services$10.00
2Azure$10.00
3NanoGPT$19.00
4DevPass (LLM Gateway)$25.00
The cheapest paid channel is the only channel.
Related models
Ministral 3 14B Instructsame series$0.37 / $0.50Ministral 3 14Bsame series$0.20 / $0.20Ministral 3 3B Reasoning 2512same series$1.04 / $0.548Llama 4 Maverick 17B 128E Instruct FP8cheaper alternative$0 / $0Lyria 3 Clip Previewcheaper alternative$0 / $0Lyria 3 Pro Previewcheaper alternative$0 / $0
Price historyone sample accumulated per data sync
Input listOutput listMin blended