Mistral
Ministral 3 14B
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Model facts
- Context window
- 262K tokens
- Maximum output
- 128K tokens
- Cheapest paid input
- $0.2 per 1M tokens
- Cheapest paid output
- $0.2 per 1M tokens
- Open weights
- yes
- Providers
- 3
Capabilities and modalities
tool calling, structured output, attachments, temperature control, open weights, text, image.
Artificial Analysis benchmarks
Compare this model on the full LLM benchmark leaderboard.
| Configuration | AAI | Coding | Math | Output tokens/s |
|---|---|---|---|---|
| default | 11.2 | 14.4 | 30.0 | 97.0 |
Observed price history
- 2026-08-24: $0.2 input / $0.2 output per 1M tokens
API providers
- DigitalOcean — model id mistral-3-14B; $0.2 input / $0.2 output per 1M tokens; provider documentation
- NanoGPT — model id mistralai/ministral-14b-instruct-2512; $0.1 input / $0.4 output per 1M tokens; provider documentation
- Infomaniak — model id mistralai/Ministral-3-14B-Instruct-2512; $0.37 input / $0.5 output per 1M tokens; provider documentation