# Ministral 3 14B Instruct 2512

Ministral 3 14B Instruct 2512 is a language model from Mistralai with a 256K-token context window. Provider list price is $0.20 per million input tokens and $0.20 per million output; on Allocate you pay $0.21 and $0.21 with the 7% transaction fee. The weights are open under Apache 2.0, so you can fine-tune it and own the result.

## Pricing

| | Provider list | On Allocate |
| --- | --- | --- |
| Input, per M tokens | $0.20 | $0.21 |
| Output, per M tokens | $0.20 | $0.21 |

Token usage bills at the provider list price plus the 7% transaction fee. Prices checked 2026-07-08.

## Facts

| Field | Value |
| --- | --- |
| Lab | Mistralai |
| Modality | Language |
| Context window | 256K tokens |
| License | Apache 2.0 |
| Open weights | Yes |
| Fine-tunable | Yes, on your data |
| Catalog id | mistral/ministral-3-14b-instruct-2512 |

## What a real workload costs

Take 1,000,000 requests a month at 1,200 input and 350 output tokens each: 1,200M input and 350M output tokens. At list prices that is 1,200 × $0.20 + 350 × $0.20 = $310 a month. Billed on Allocate it is $331.70 with the 7% transaction fee.

## Common questions

### How much does Ministral 3 14B Instruct 2512 cost per million tokens?

Provider list price is $0.20 per million input tokens and $0.20 per million output tokens. On Allocate you pay list plus the 7% transaction fee: $0.21 in and $0.21 out.

### What context window does Ministral 3 14B Instruct 2512 have?

262,144 tokens (256K). At roughly 0.75 words per token, that is about 197k words of English text per request.

### Can I fine-tune Ministral 3 14B Instruct 2512?

Yes. Ministral 3 14B Instruct 2512 is an open-weights model under the Apache 2.0 license. The license is permissive, so the fine-tuned weights are yours to use commercially. On Allocate the trained weights stay inside your boundary and belong to you.

### How do I call Ministral 3 14B Instruct 2512 on Allocate?

Send mistral/ministral-3-14b-instruct-2512 in the model field of the OpenAI-compatible endpoint at api.allocate.network/v1, or point a route name (like prod/support-agent) at it so you can swap the model later without a deploy.

---

[HTML page](https://allocate.network/models/mistral-ministral-3-14b-instruct-2512) · [Machine-readable catalog](https://allocate.network/catalog.json)