Identity
- Status
- active
- Developer ID
mistralai/Ministral-3-14B-Base-2512- Released
- Not reported
- Version
- Ministral-3-14B-Base-2512
- License
- apache-2.0
Mistral AIMinistral 3 14B Base 2512
Ministral-3-14B-Base-2512 is an open-weight vision-language model published by Mistral AI.
- Token context
- 262K tokens
- Inputs
- Text, Image
- Outputs
- Text
- Released
- Not reported
Providers & Pricing
0 current hosted offerings
No Current Hosted API Offering Verified
No exact current provider endpoint or published price has been verified for this model version.
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 13.9B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- Unknown
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- Yes
- Tool calling
- No
- Capabilities
- generation
This page represents one developer model product. Dated API snapshots, serving endpoints, pricing, regions, quantizations, and service tiers attach as versioned aliases or provider details and never create duplicate public model records.
Version Lineage
PredecessorUnknown
SuccessorsUnknown
Aliasesmistralai/Ministral-3-14B-Base-2512, mistralai/Ministral-3-14B-Base-2512
Explicit Unknowns
- Release date
- Maximum output
- Knowledge cutoff
- API availability
- Provider pricing
Primary Evidence
Sources and Observation Date
mistralai/Ministral-3-14B-Base-2512 developer model repositoryMistral AI · observed Aug 28, 2026mistralai/Ministral-3-14B-Base-2512 config.json at 5b0ceedbb42dMistral AI · observed Aug 28, 2026mistralai/Ministral-3-14B-Base-2512 README.md at 5b0ceedbb42dMistral AI · observed Aug 28, 2026mistralai/Ministral-3-14B-Base-2512 immutable Hub API metadataMistral AI · observed Aug 28, 2026mistralai/Ministral-3-14B-Base-2512 tokenizer_config.json at 5b0ceedbb42dMistral AI · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Ministral 3 14B Base 2512Mistral AI | vs |  Qwen3.8 27BQwen | cross-developer peersimage, text |
Ministral 3 14B Base 2512Mistral AI | vs |  Gemma 4 12BGoogle DeepMind | cross-developer peersimage, text |
Ministral 3 14B Base 2512Mistral AI | vs | cross-developer peersimage, text | |
Ministral 3 14B Base 2512Mistral AI | vs | Ministral 3 14B Instruct 2512Mistral AI | family variantsimage, text |
Ministral 3 14B Base 2512Mistral AI | vs | Ministral 3 14B Reasoning 2512Mistral AI | family variantsimage, text |
Ministral 3 14B Base 2512Mistral AI | vs | Ministral 3 8B Base 2512Mistral AI | family variantsimage, text |
Ministral 3 14B Base 2512Mistral AI | vs | Ministral 8B Instruct 2410Mistral AI | family variantstext |
Ministral 3 14B Base 2512Mistral AI | vs |  PaddleOCR VL 1.5Baidu | cross-developer peersimage, text |
Ministral 3 14B Base 2512Mistral AI | vs | cross-developer peersimage, text |
Questions
Ministral 3 14B Base 2512 FAQs
What is Ministral 3 14B Base 2512?+
Ministral-3-14B-Base-2512 is an open-weight vision-language model published by Mistral AI. It is developed by Mistral AI and its current sourced lifecycle status is active.
What inputs and outputs does Ministral 3 14B Base 2512 support?+
Ministral 3 14B Base 2512's current record lists Text and Image as input and Text as output.
How much context does Ministral 3 14B Base 2512 support?+
The current record lists a 262K-token context window and does not report a maximum output length.
Is Ministral 3 14B Base 2512 available through an API?+
Ministral 3 14B Base 2512's current primary-source record does not establish API availability. No provider endpoint is treated as available without direct provider evidence.
How large is Ministral 3 14B Base 2512?+
The current record lists 13.9B total parameters and an unknown active parameter count. Its architecture is Mistral3ForConditionalGeneration.
What capabilities and tasks does Ministral 3 14B Base 2512 support?+
Ministral 3 14B Base 2512's recorded capabilities are generation. Its supported tasks are image and text.
How much does Ministral 3 14B Base 2512 cost through an API?+
No directly sourced token price is currently attached to Ministral 3 14B Base 2512. Missing prices remain unknown rather than being inferred from another model or provider.
Can Ministral 3 14B Base 2512 be self-hosted?+
Ministral 3 14B Base 2512 is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Ministral 3 14B Base 2512 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are mistralai/Ministral-3-14B-Base-2512.
Which models can Ministral 3 14B Base 2512 be compared with?+
The current compatible peer set includes Qwen3.8 27B, Gemma 4 12B, Llama 4 Scout 17B 16E, Ministral 3 14B Instruct 2512, and Ministral 3 14B Reasoning 2512. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →