Mistral

About Mistral

Our mission is to make frontier AI open to all, and together solve the world's hardest problems.

We partner with organizations in high-stakes industries like finance, manufacturing, defense, energy, and the public sector to co-create tailored AI systems to solve their hardest, most high-value problems. Because we believe that this critical stake for companies requires deep control, ownership, and production reliability, we have built full-stack AI solutions, including frontier models, developer tools, applications, and compute.

Website ↗Documentation ↗

Source ↗ · 2026-11-12T02:17:02.963004760Z

Transparency & Governance

  • Foundation Model Transparency Index 2025 · 18 / 100 · Company disclosure assessment Source assessment ↗

206 indexed models

206 matching models

Ministral 14B

vercelAIGatewayCatalog/mistral/ministral-14b

Ministral 3 14B is the largest model in the Ministral 3 family, offering state-of-the-art capabilities and performance comparable to its larger Mistral Small 3.2 24B counterpart. Optimized for local deployment, it delivers high performance across diverse hardware, including local

Context window
262,144
Maximum output
256,000
Input modalities
text, image, pdf
Output modalities
text

Ministral 14B 3.0

awsBedrock/mistral.ministral-3-14b-instruct

Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

Ministral 3 8B

awsBedrock/mistral.ministral-3-8b-instruct

Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

ministral-3b

cheaperInference/ministral-3b

Context window
128,000
Maximum output
4,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput

Inference prices

Ministral 3B

awsBedrock/mistral.ministral-3-3b-instruct

Input modalities
text, image
Output modalities
text
Capabilities
multimodal, visionInput

Ministral 3B

vercelAIGatewayCatalog/mistral/ministral-3b

A compact, efficient model for on-device tasks like smart assistants and local analytics, offering low-latency performance.

Context window
131,072
Maximum output
4,000
Input modalities
text, image
Output modalities
text

Ministral 3B · azureml-mistral v1

azureFoundry/azureml-mistral/Ministral-3B@1

Ministral 3B is a state-of-the-art Small Language Model (SLM) optimized for edge computing and on-device applications. As it is designed for low-latency and compute-efficient inference, it it also the perfect model for standard GenAI applications that have

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text
Capabilities
toolCalling

ministral-8b

cheaperInference/ministral-8b

Context window
128,000
Maximum output
4,000
Input modalities
text, image
Output modalities
text
Capabilities
multimodal, structuredOutputs, toolCalling, visionInput

Inference prices

Ministral 8B

vercelAIGatewayCatalog/mistral/ministral-8b

A more powerful model with faster, memory-efficient inference, ideal for complex workflows and demanding edge applications.

Context window
262,144
Maximum output
4,000
Input modalities
text, image
Output modalities
text

Ministral 8B · azureml-mistral v1

azureFoundry/azureml-mistral/Ministral-8B@1

Ministral 8B is a state-of-the-art Small Language Model (SLM) optimized for edge computing and on-device applications. As it is designed for low-latency and compute-efficient inference, it it also the perfect model for standard GenAI applications that have

Context window
131,072
Maximum output
4,096
Input modalities
text
Output modalities
text

Mistral 7B Instruct

awsBedrock/mistral.mistral-7b-instruct-v0:2

Input modalities
text
Output modalities
text

Mistral-7B-Instruct-v0.1

vertexAI/publishers/mistral-ai/models/mistral@mistral-7b-instruct-v0.1

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 54.964%
  • Open LLM Leaderboard v2: 12.771%

Mistral-7B-v0.1

vertexAI/publishers/mistral-ai/models/mistral@mistral-7b-v0.1

Input modalities
text
Output modalities
text

Benchmarks

  • LLM-Perf: 321,755.425
  • Open LLM Leaderboard v1: 60.969%
  • Open LLM Leaderboard v2: 14.575%

Mistral-7B-v0.3

vertexAI/publishers/mistral-ai/models/mistral@mistral-7b-v0.3

Input modalities
text
Output modalities
text

Benchmarks

  • Open LLM Leaderboard v1: 60.282%
  • Open LLM Leaderboard v2: 14.23%

mistralai/Codestral-22B-v0.1

huggingface/mistralai/Codestral-22B-v0.1

Input modalities
text
Output modalities
text

Benchmarks

  • LLM Stats · GitHub archive: 0.782
  • Open LLM Leaderboard v2: 23.28%

mistralai/Devstral-Small-2-24B-Instruct-2512

azureFoundry/HuggingFace/mistralai-devstral-small-2-24b-instruct-2512@2

`mistralai/Devstral-Small-2-24B-Instruct-2512` powered by vLLM - [Original Model Card](https://huggingface.co/mistralai/Devstral-Small-2-24B-Instruct-2512) - [vLLM Documentation](https://docs.vllm.ai/) ## Chat Completions API ### Send Request You can use cURL or any REST Clie

Input modalities
text
Output modalities
text

mistralai/Devstral-Small-2505

vertexAI/publishers/hf-mistralai/models/devstral-small-2505@001

Input modalities
text
Output modalities
text

Benchmarks

  • SWE-bench: 46.8%

Models

Loading
EVIDENCE / COMPARISON

Benchmarks

Explore every benchmark

Loading

These charts contain model-linked results. The charts above also include unlinked source profiles. Compare scores within each evaluation. Model quality, usage, transparency and system performance measure different things.

Install TensorTrace