Mistral Large 4 in Langdock
Mistral Large 4 is Mistral AI’s open-weight, general-purpose multimodal model. In Langdock it is available with hosting in the EU. You can use it in chat, in agents and workflows, and via the API, where it costs €0.70 per 1 million input tokens and €2.10 per 1 million output tokens.
Written by LangdockUpdated
What is Mistral Large 4 good at?
Mistral AI names these typical uses for Mistral Large 4[1]:
- General-purpose work with text and images
- Function calling, so the model can use tools
- Structured outputs
- Questions about documents
This is how Mistral AI describes the model, not a test result of ours. Which tools the model can use in Langdock depends on the tools and integrations enabled in your workspace.
What are the key facts for Mistral Large 4 in Langdock?
| Fact | Value |
|---|---|
| Provider | Mistral AI[3] |
| Name in the model selector | Mistral Large 4[3] |
| Hosting region in Langdock | EU[3] |
| Price per 1M input tokens | €0.70[3] |
| Price per 1M output tokens | €2.10[3] |
| Context window documented by Mistral AI | 1M tokens[1] |
| Input types documented by Mistral AI | Text and images[1] |
The limits Mistral AI documents apply to its own API; Langdock can set its own. The context window indicator next to the model selector shows the window size in use.
Token prices apply to the API, to model use in workflows and to extra usage, excluding VAT. They are converted from US dollars at the current exchange rate, so they can change slightly from day to day. In chat and agents, Core and Work seats with included models have no usage-based costs; pricing lists the plans.
When should you choose Mistral Large 4, and when another model?
Mistral AI lists Mistral Large 4 as a featured general-purpose model and publishes its weights under the Mistral Ecosystem Open Weight License. That makes it the model to look at when an open-weight model is a requirement.[1][2]
The table compares what Langdock lists for Mistral Large 4 and for the alternatives. The model list has every model.
| Model | Provider | Hosting region | Input / output per 1M tokens |
|---|---|---|---|
| Mistral Large 4 | Mistral AI | EU | €0.70 / €2.10 |
| Claude Sonnet 5.5 | Anthropic | EU | €2 / €10.02 |
| GPT-6.1 Terra | OpenAI | EU | €1 / €5.01 |
| Gemini 4 Argon | EU | €2 / €10.02 |
How do you use Mistral Large 4 in Langdock?
- Chat: choose Mistral Large 4 in the model selector of the chat input. You can switch models in the middle of a conversation and set a personal default model.
- Agents: choose the model in the agent editor.
- API: the Agents API lists the models you can use for agents in your workspace.
- Admins: workspace admins enable or disable each model in the workspace settings and choose the default model for new chats and agents. If you do not see the model, ask your admin.
Details are in the model guide of the documentation.
Where is Mistral Large 4 hosted, and what happens to your data?
The Langdock model list shows the hosting region EU for Mistral Large 4[3]. In a new workspace only models hosted in the EU are enabled by default; admins decide which other models are switched on[7].
For all models, Langdock states that customer data is never used to train or improve AI models[8], and it publishes a data processing agreement (DPA)[9]. A hosting region alone does not make a use case GDPR-compliant: the guide to GDPR-compliant AI explains what Langdock provides and what remains your responsibility.
Frequently asked questions
Sources
- Mistral AI: Mistral Large 4 model page (checked on )
- Mistral AI: Models overview (checked on )
- Langdock: Models with hosting region
- Langdock documentation: Model guide
- Langdock documentation: Agent configuration
- Langdock documentation: Models for the Agents API
- Langdock documentation: Workspace settings, models
- Langdock: Security
- Langdock: Data processing agreement (DPA)
Mistral Large 4 is a product of Mistral AI. Product names are trademarks of their owners. Statements about the model were taken from Mistral AI’s documentation on the date shown in the sources.
Related pages
- Claude Sonnet 5.5 in LangdockClaude Sonnet 5.5 is the Claude model Anthropic describes as its best combination of speed and intelligence.
- GPT-6.1 Terra in LangdockGPT-6.1 Terra is OpenAI’s fast, efficient model for visual reasoning, precise computer use and clear, natural writing.
- Gemini 4 Argon in LangdockGemini 4 Argon is the model Google describes as its efficient Gemini 4 reasoning model.
- All AI models in LangdockEvery model with hosting region and token prices.
- GDPR-compliant AI for companiesWhat Langdock provides and what stays with you as the controller.