Mistral: Ministral 3 14B 2512
Mistral Ministral 3 14B 2512 from MistralAI supports both text and image inputs within a substantial context length of 262,144 tokens, making it suitable for complex tasks that require handling multiple types of data. It also offers the flexibility to use external tools, though it lacks support for structured output or advanced reasoning capabilities. Given its price at $0.2 per million input and output tokens, Mistral may be a cost-effective choice for projects involving text and image processing. However, with no benchmark coverage yet, users should consider this model as part of a broader evaluation before making a decision.
- Model ID
- mistralai/ministral-14b-2512
- Vendor
- mistralai
- Released
- December 2025
- Tokenizer
- Mistral
- Input Modalities
- text, image
- Output Modalities
- text
- Max Output
- 209,715 tokens
- Tool Calling
- ✓ supported
- Structured Output
- ✓ supported
- Reasoning Mode
- not supported
- Vision
- ✓ accepts images
- Audio
- no
- Moderated
- no
What it costs in practice
Computed from the current $0.20/M input and $0.20/M output rates. Run your own numbers →
| Job | Tokens | Cost |
|---|---|---|
| Summarize a 50-page report | 30k in / 1.5k out | under $0.01 |
| Classify 1,000 customer emails | 500k in / 50k out | $0.11 |
| A month of a busy support chatbot | 5M in / 2M out | $1.40 |
Similar models
Mistral: Ministral 3 8B 2512
Mistral: Mistral Small 3.2 24B
Mistral: Codestral 2508 (batch)
Mistral: Ministral 3 8B 2512 (batch)
Mistral: Mistral Medium 3.5
Mistral: Mistral Medium 3.5 (batch)
Quick answers
- How much does Mistral: Ministral 3 14B 2512 cost?
- $0.20 per million input tokens and $0.20 per million output tokens.
- What is Mistral: Ministral 3 14B 2512's context window?
- 262,144 tokens, roughly 393 pages of text in a single request.
- Does Mistral: Ministral 3 14B 2512 support tool calling?
- It supports tool calling, structured output.
- Can Mistral: Ministral 3 14B 2512 process images?
- Yes, it accepts image input.