Identity
- Status
- active
- Developer ID
mistralai/Ministral-3-3B-Instruct-2512- Released
- Not reported
- Version
- Ministral-3-3B-Instruct-2512
- License
- apache-2.0
Mistral AIMinistral 3 3B Instruct 2512
Ministral-3-3B-Instruct-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
Estimate workload cost →| Provider | Input / 1M | Output / 1M | Cache read / 1M | Cache write / 1M | Observed | Evidence |
|---|---|---|---|---|---|---|
 OpenrouterAvailable | $0.10 | $0.10 | $0.010 | — | Aug 29, 2026 | Provider-reported |
At a Glance
Model Facts
Capacity
- Token context
- 262K tokens
- Maximum output
- Unknown
- Total parameters
- 3.8B
- Active parameters
- Unknown
- Knowledge cutoff
- Not reported
Interface and Access
- Inputs
- Text, Image
- Outputs
- Text
- API available
- Yes
- Open weights
- Yes
- Self-hostable
- Yes
- Reasoning
- No
- Vision
- Yes
- Tool calling
- Yes
- Capabilities
- chat, generation, tools
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-3-3B-Instruct-2512, mistralai/Ministral-3-3B-Instruct-2512
Explicit Unknowns
- Release date
- Maximum output
- Knowledge cutoff
Primary Evidence
Sources and Observation Date
mistralai/Ministral-3-3B-Instruct-2512 developer model repositoryMistral AI · observed Aug 28, 2026OpenRouter mistralai/ministral-3b-2512 model APIOpenRouter · observed Aug 29, 2026mistralai/Ministral-3-3B-Instruct-2512 config.json at b35d4dfe56c1Mistral AI · observed Aug 28, 2026mistralai/Ministral-3-3B-Instruct-2512 README.md at b35d4dfe56c1Mistral AI · observed Aug 28, 2026mistralai/Ministral-3-3B-Instruct-2512 immutable Hub API metadataMistral AI · observed Aug 28, 2026mistralai/Ministral-3-3B-Instruct-2512 tokenizer_config.json at b35d4dfe56c1Mistral AI · observed Aug 28, 2026Hugging Face catalogHugging Face · observed Sep 2, 2026
Comparable Peers
Related Model Comparisons
| A | Pair | B | Context |
|---|---|---|---|
Ministral 3 3B Instruct 2512Mistral AI | vs |  Gemma 4 12BGoogle DeepMind | cross-developer peersimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs | cross-developer peerstext | |
Ministral 3 3B Instruct 2512Mistral AI | vs | cross-developer peersimage, text | |
Ministral 3 3B Instruct 2512Mistral AI | vs | Ministral 3 3B Base 2512Mistral AI | family variantsimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs | Ministral 3 3B Reasoning 2512Mistral AI | family variantsimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs | Ministral 3 8B Base 2512Mistral AI | family variantsimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs | Ministral 3 8B Instruct 2512Mistral AI | family variantsimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs |  PaddleOCR VL 1.5Baidu | cross-developer peersimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs |  Qwen3.5 35B A3BQwen | cross-developer peersimage, text |
Ministral 3 3B Instruct 2512Mistral AI | vs |  GLM OCRZ.ai | cross-developer peersimage, text |
Questions
Ministral 3 3B Instruct 2512 FAQs
What is Ministral 3 3B Instruct 2512?+
Ministral-3-3B-Instruct-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 3B Instruct 2512 support?+
Ministral 3 3B Instruct 2512's current record lists Text and Image as input and Text as output.
How much context does Ministral 3 3B Instruct 2512 support?+
The current record lists a 262K-token context window and does not report a maximum output length.
Is Ministral 3 3B Instruct 2512 available through an API?+
Ministral 3 3B Instruct 2512 is marked as API-available. The directly sourced provider records currently include Openrouter.
How large is Ministral 3 3B Instruct 2512?+
The current record lists 3.8B total parameters and an unknown active parameter count. Its architecture is Mistral3ForConditionalGeneration.
What capabilities and tasks does Ministral 3 3B Instruct 2512 support?+
Ministral 3 3B Instruct 2512's recorded capabilities are chat, generation, and tools. Its supported tasks are image and text.
How much does Ministral 3 3B Instruct 2512 cost through an API?+
The lowest directly sourced prices currently attached to Ministral 3 3B Instruct 2512 are $0.10 per million input tokens through Openrouter and $0.10 per million output tokens through Openrouter. Prices are provider-specific and should be checked against each cited observation date.
Can Ministral 3 3B Instruct 2512 be self-hosted?+
Ministral 3 3B Instruct 2512 is an open-weight model. Self-hosting is supported, and the recorded license is apache-2.0.
Does Ministral 3 3B Instruct 2512 have related versions or aliases?+
No predecessor is recorded. No successor is recorded. Recorded aliases are mistralai/Ministral-3-3B-Instruct-2512.
Which models can Ministral 3 3B Instruct 2512 be compared with?+
The current compatible peer set includes Gemma 4 12B, Granite 4.1 3B, Granite Vision 4.1 4B, Ministral 3 3B Base 2512, and Ministral 3 3B Reasoning 2512. Compatibility requires shared sourced modalities and tasks; it does not imply that one model is better. Browse model comparisons →