Mistral: Ministral 3 14B 2512
Compact Mistral model for edge, latency-sensitive, and cost-efficient workloads
Cheapest input
$0.2
$/MTok · models.dev
Cheapest output
$0.2
$/MTok
Context
262K
tokens
Offers
7
3 sources
Offers
Same model, different listings. First-party, router, and aggregator rows stay separate so you can see the spread instead of a single blended number.
| Source | Provider | Input | Output | Cache read | Context |
|---|---|---|---|---|---|
| models.devcheapestmistralai/ministral-14b-2512 | Kilo Gateway | $0.2 | $0.2 | $0.02 | 262K |
| models.devmistralai/ministral-14b-2512 | NanoGPT | $0.2 | $0.2 | $0 | 262K |
| OpenRoutermistralai/ministral-14b-2512 | OpenRouter | $0.2 | $0.2 | $0.02 | 262K |
| models.devministral-14b-2512 | LLM Gateway | $0.2 | $0.2 | $0 | 262K |
| LiteLLMmistralai/ministral-14b-2512 | — | $0.2 | $0.2 | $0.02 | — |
| LiteLLMministral-14b-2512 | — | $0.2 | $0.2 | $0.02 | — |
| models.devministral-14b-2512 | 302.AI | $0.33 | $0.33 | $0 | 128K |
Capabilities
- Tool calling
- Structured output
- Attachments
- Open weights
- In: text
- In: image
- Out: text
Knowledge cutoff: 2024-12Released: 2025-12-16Family: ministral
Scores
Sparse coverage on purpose. Missing a score means we have not linked one yet, not that the model is unranked. Full boards on /benchmarks.
- AA intelligence11.1
- AA coding14.4
- AA agentic2.2
Sources: Arena AI, Artificial Analysis. See /benchmarks.