---
title: "mistral-medium-3.5-128b"
publisher: "mistralai"
type: "endpoint"
updated: "2026-04-29T15:16:02.842Z"
description: "A high performing model for text generation, coding and agentic use cases"
canonical: "https://build.nvidia.com/mistralai/mistral-medium-3.5-128b"
---

# Mistral Medium 3.5 128B

## Description
Mistral Medium 3.5 is Mistral AI's first flagship merged model. It is a dense 128B model with a 256k context window, handling instruction-following, reasoning, and coding in a single set of weights. Mistral Medium 3.5 replaces its predecessor Mistral Medium 3.1 and Magistral in Le Chat. It also replaces Devstral 2 in our coding agent Vibe. Concretely, expect better performance for instruct, reasoning and coding tasks in a new unified model in comparison with our previous released models.

Reasoning effort is configurable per request, so the same model can answer a quick chat reply or work through a complex agentic run. They trained the vision encoder from scratch to handle variable image sizes and aspect ratios.

*This model is ready for commercial/non-commercial use.*

## Third-Party Community Consideration:
This model is not owned or developed by NVIDIA. This model has been developed and built to a third-party's requirements for this application and use case; see link to Non-NVIDIA [Mistral Medium 3.5 128B Model Card](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B).

## License and Terms of Use:
**GOVERNING TERMS:** The trial service is governed by the [NVIDIA API Trial Terms of Service](https://assets.ngc.nvidia.com/products/api-catalog/legal/NVIDIA%20API%20Trial%20Terms%20of%20Service.pdf). Use of this model is governed by the [Modified MIT license](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B/blob/main/LICENSE).

## Deployment Geography:
Global

## Use Case:
**Use Case:** Designed for advanced chat, coding assistance, reasoning-intensive tasks, multimodal image understanding, and agentic workflows that benefit from function calling, JSON output, and long-context processing.

## Release Date:
**Build.NVIDIA.com:** 04/29/2026 via [link](https://build.nvidia.com/mistralai/mistral-medium-3.5-128b) <br>
**Huggingface:** 04/29/2026 via [link](https://huggingface.co/mistralai/Mistral-Medium-3.5-128B)

## Reference(s):
**References:**
- [Mistral Vibe](https://github.com/mistralai/mistral-vibe)
- [vLLM library](https://github.com/vllm-project/vllm)
- [llama.cpp](https://github.com/ggml-org/llama.cpp)
- [SGLang docs](https://docs.sglang.io/basic_usage/send_request.html)
- [Transformers](https://github.com/huggingface/transformers)
- [LM Studio model page](https://lmstudio.ai/)
- [Axolotl](https://github.com/axolotl-ai-cloud/axolotl/tree/main/examples/mistral4)
- [Unsloth](https://unsloth.ai/)

## Model Architecture:
**Architecture Type:** Transformer  
**Network Architecture:** Mistral (dense 128B language model with vision encoder)  
**Total Parameters:** 128B

### Input:
**Input Types:** Text, Image  
**Input Formats:** String, Red, Green, Blue (RGB)  
**Input Parameters:** One-Dimensional (1D), Two-Dimensional (2D)  
**Other Input Properties:** Supports multilingual text input in English, French, Spanish, German, Italian, Portuguese, Dutch, Chinese, Japanese, Korean, and Arabic, plus image input with variable image sizes and aspect ratios.  
**Input Context Length (ISL):** 262,144 (256k)

### Output:
**Output Types:** Text  
**Output Format:** String  
**Output Parameters:** One-Dimensional (1D)  
**Other Output Properties:** Supports native function calling, JSON output, configurable reasoning effort for quick replies or deeper reasoning runs, and strong system prompt adherence.

__Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA's hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions.__

## Software Integration:
**Runtime Engines**
- **vLLM**
- **SGLang**
- **Transformers** 
- **llama.cpp**
- **LM Studio**

**Supported Hardware:**
- **NVIDIA Ampere:** A100
- **NVIDIA Blackwell:** B100, B200, GB200
- **NVIDIA Hopper:** H100, H200

**Operating Systems:** Linux

__The integration of foundation and fine-tuned models into AI systems requires additional testing using use-case-specific data to ensure safe and effective deployment. Following the V-model methodology, iterative testing and validation at both unit and system levels are essential to mitigate risks, meet technical and functional requirements, and ensure compliance with safety and ethical standards before deployment.__

## Model Version(s)
Mistral Medium 3.5 128B v3.5

## Training, Testing, and Evaluation Datasets:

### Training Dataset
**Data Modality:** Image, Text  
**Image Training Data Size:** Undisclosed   
**Text Training Data Size:** Undisclosed    
**Training Data Collection:** Undisclosed   
**Training Labeling:** Undisclosed  
**Training Properties:** Undisclosed    

### Testing Dataset
**Testing Data Collection:** Undisclosed  
**Testing Labeling:** Undisclosed  
**Testing Properties:** Undisclosed

### Evaluation Dataset
**Evaluation Data Collection:** Undisclosed  
**Evaluation Labeling:** Undisclosed  
**Evaluation Properties:** Undisclosed

## Inference
**Acceleration Engine:** vLLM  
**Test Hardware:** NVIDIA H100

## Additional Details
### Recommended Deployment Settings
Use `reasoning_effort="high"` for complex prompts and agentic coding tasks. Recommended temperature settings are `0.7` for `reasoning_effort="high"` and `0.0` to `0.7` for `reasoning_effort="none"` depending on the task.

### Deployment Options
Supported deployment options include vLLM, llama.cpp, LM Studio, SGLang, and Transformers.

### Mistral Vibe Integration
Mistral Vibe support includes a local vLLM configuration path with a dedicated system prompt, a local model alias, and a configurable local server endpoint.

For more information, please refer to the [Mistral Vibe README](https://github.com/mistralai/mistral-vibe/blob/main/README.md).

### Vision and Agentic Capabilities
The model supports system prompts, multimodal image analysis, native function calling, JSON output, and agentic workflows. The vision encoder is designed to handle variable image sizes and aspect ratios.

## Ethical Considerations
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.

Please make sure you have proper rights and permissions for all input image content; if image includes people, personal health information, or intellectual property, the image generated will not blur or maintain proportions of image subjects included.

Please report model quality, risk, security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

## Prototype

```python
import requests

invoke_url = "https://integrate.api.nvidia.com/v1/chat/completions"

headers = {
"Authorization": "Bearer ",
"Accept": "application/json",
}

payload = {
"messages": [
{
"role": "user",
"content": ""
}
]
}

# re-use connections
session = requests.Session()

response = session.post(invoke_url, headers=headers, json=payload)

response.raise_for_status()
response_body = response.json()
print(response_body)
```

```javascript
import fetch from "node-fetch";

const invokeUrl = "https://integrate.api.nvidia.com/v1/chat/completions"

const headers = {
"Authorization": "Bearer ",
"Accept": "application/json",
}

const payload = {
"messages": [
{
"role": "user",
"content": ""
}
]
}

let response = await fetch(invokeUrl, {
method: "post",
body: JSON.stringify(payload),
headers: { "Content-Type": "application/json", ...headers }
});

let response_body = await response.json()

console.log(JSON.stringify(response_body))
```

```bash
invoke_url='https://integrate.api.nvidia.com/v1/chat/completions'

authorization_header='Authorization: Bearer '
accept_header='Accept: application/json'
content_type_header='Content-Type: application/json'

data=$'{
"messages": [
{
"role": "user",
"content": ""
}
]
}'

response=$(curl --silent -i -w "\n%{http_code}" --request POST \
--url "$invoke_url" \
--header "$authorization_header" \
--header "$accept_header" \
--header "$content_type_header" \
--data "$data"
)

echo "$response"
```