Mistral AI model product
Min istral 3
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities.
Updated Aug 17, 2026. Default version: Min istral 3 (3B Reasoning 2512)
LLMBoard Score20.1Min istral 3 (3B Reasoning 2512)
Coverage60%4 benchmark families
Context window131.1KTokens
Official input price$0.04Mistral API
Min istral 3 Capability Profile
This profile uses the model's current scored version. Arena ratings and prices are shown separately.
Min istral 3 Benchmark Results
Benchmark scores for Min istral 3 (3B Reasoning 2512).
Sort by
Benchmark | Score | Rank | Participants | Percentile | Evidence | Evaluated |
|---|
| BenchmarkAIME 2024 | Score77.5% | Rank33 | Participants53 | Percentile38.5% | EvidenceC | Evaluated |
| BenchmarkLiveCodeBench | Score54.8% | Rank40 | Participants75 | Percentile47.3% | EvidenceC | Evaluated |
| BenchmarkAIME 2025 | Score72.1% | Rank84 | Participants115 | Percentile27.2% | EvidenceC | Evaluated |
| BenchmarkGPQA | Score53.4% | Rank174 | Participants239 | Percentile27.3% | EvidenceC | Evaluated |
Min istral 3 Arena Results
Preference and agent-evaluation results for the default version.
No Arena results
The default version does not have a matching Arena result yet.
Min istral 3 Pricing
Official vendor API pricing appears first, followed by individual provider offers.
- Official API
- $0.04 input, $0.04 output per 1M
- Official provider
- Mistral
- Lowest third-party
- From $1.04 input, $0.5483 output per 1M via Clarifai
- Tracked offerings
- 2
Sort by
Provider | Provider model ID | Region | Input / 1M | Output / 1M | Context | Updated |
|---|
| ProviderMistral | Provider model IDministral-3b-latest | Regionglobal | Input / 1M$0.04 | Output / 1M$0.04 | Context128K | Updated |
| ProviderClarifai | Provider model IDmistralai/completion/models/Ministral-3-3B-Reasoning-2512 | Regionglobal | Input / 1M$1.04 | Output / 1M$0.5483 | Context262.1K | Updated |
Official prices use only the vendor's configured official Provider and positive standard USD PAYG rates. Third-party offers remain explicitly labeled.
Min istral 3 Runtime Performance
Provider-specific output speed and catalog latency for Min istral 3 (3B Reasoning 2512). Runtime does not affect the capability score.
Sort by
Provider | Output Speed | Catalog Latency | Max Input | Max Output | Updated |
|---|
| ProviderMistral AI | Output Speed1,222 tok/s | Catalog Latency0.16 s | Max Input131.1K | Max Output131.1K | Updated |
Output Speed is generated output tokens received per second. Catalog latency is reported separately from observed provider TTFT.
Min istral 3 Specifications
Technical details for the model's default version.
- Version
- Min istral 3 (3B Reasoning 2512)
- Released
- Dec 4, 2025
- Knowledge cutoff
- Unknown
- Parameters
- 3B
- Context window
- 131.1K
- Max output
- 131.1K
- Inputs
- image, text
- Outputs
- text
- Open weights
- No
- License
- Apache 2.0
Min istral 3 Versions
Available versions of this model. The score column identifies the version used in the overall ranking.
Sort by
Version | Released | LLMBoard | Parameters | Context | Max output | Open weights | License |
|---|
| VersionMin istral 3 (3B Reasoning 2512) | Released | LLMBoard20.1 | Parameters3B | Context131.1K | Max output131.1K | Open weightsNo | LicenseApache 2.0 |
Min istral 3 vs nearby models
Open a comparison with the three ranked models immediately above and below this model.
Models similar to Min istral 3
Recommendations prioritize the same model type and family, then the closest LLMBoard score.
MA
Pixtral Large
Mistral AI
MA
Magistral Small
Mistral AI
MA
Magistral Medium
Mistral AI
MA
Devstral Medium
Mistral AI
MA
Devstral Small 1.1
Mistral AI
MA
Mistral Small 3.2 24B
Mistral AI
What is Min istral 3?
Key information about Min istral 3 and its available data.
The smallest model in the Ministral 3 family, Ministral 3 3B is a powerful, efficient tiny language model with vision capabilities. This model is the reasoning post-trained version, trained for reasoning tasks, making it ideal for math, coding and stem related use cases.
The Ministral 3 family is designed for edge deployment, capable of running on a wide range of hardware. Ministral 3 3B can even be deployed locally, fitting in 16GB of VRAM in BF16, and less than 8GB of RAM/VRAM when quantized.
Data as of 2026-08-17.
FAQ
Common questions about Min istral 3.
When was Min istral 3 released?
Min istral 3's default version was released on Dec 4, 2025.
How much does Min istral 3 cost?
Min istral 3's official API price is $0.04 per million input tokens and $0.04 per million output tokens via Mistral. The lowest tracked third-party offer starts at $1.04 input and $0.5483 output via Clarifai.
Who created Min istral 3?
Min istral 3 was created by Mistral AI.
What is the context window for Min istral 3?
The default version has a 131.1K token context window.
Is Min istral 3 open weight?
No. The default version is not marked as having publicly available weights.
How many API providers offer Min istral 3?
2 provider offerings are linked to the default version.
What models should I compare Min istral 3 with?
Nearby ranked alternatives include Gemini 2.0 Flash Lite, Grok 2, Nova Pro.