# Update of the AI Assistants module: Mistral, DeepSeek and OpenAI reasoning and deep search models

**URL:** <https://www.dolibarr.org/forum/t/update-of-the-ai-assistants-module-mistral-deepseek-and-openai-reasoning-and-deep-search-models/30107>\
**Category:** DoliStore's external modules\
**Tags:** AI\
**Created:** [March 18, 2025, 6:36am UTC](https://www.dolibarr.org/forum/t/update-of-the-ai-assistants-module-mistral-deepseek-and-openai-reasoning-and-deep-search-models/30107 "2025-03-18T06:36:34Z")\
**Posts on this page:** 1\
**Page:** 1

<div class="post-metadata">

**Author:** ![caos30](https://www.dolibarr.org/forum/user_avatar/www.dolibarr.org/caos30/32/6733_2.png) [@caos30](https://www.dolibarr.org/forum/u/caos30)\
**Post date:** [March 18, 2025, 6:36am UTC](https://www.dolibarr.org/forum/t/update-of-the-ai-assistants-module-mistral-deepseek-and-openai-reasoning-and-deep-search-models/30107/1 "2025-03-18T06:36:35Z")

</div>

After almost two months of preparation, I present to you the new update of the “AI Assistants” module for Dolibarr. This version incorporates important new features that significantly expand its capabilities.

## New integrated models

### DeepSeek

The disruptive Chinese model DeepSeek has been quite a revelation:

- Extremely fast
- Truly multilingual (even in Catalan)
- Its R1 reasoning model transparently shows the “chain of thought” (CoT)

 ![assistants-deepseek-reasoning-ENGLISH](https://www.dolibarr.org/forum/uploads/dolibarrorg/original/2X/4/4c42c37a66c04cfa2641ffda21092d28d8eadfd1.png)

### Mistral

I have also integrated the Mistral API, _the promising European LLM of the french startupt_ with the same name, that offers:

- Fast response time
- Very competitive prices
- Excellent performance in European languages
- Vision capabilities (image analysis) at economical prices

### Updates to existing providers

- **OpenAI** : Incorporation of the “economical” reasoning models o1-mini and o3-mini
- **Perplexity** : Update to the Sonar and Sonar-pro family with “Reasoning” and “DeepResearch” variants

## Interface improvements

I have redesigned the model selector, grouping them into two categories:

- Conversation
- Image generation

Conversational models now include icons indicating their special capabilities:

- 👁 Vision
- 🔎 Web search
- 🧠 Reasoning

Remember that you can change the model at any time during a conversation to optimize costs.

## Complexity in API pricing

Pricing is becoming more complex due to so many capabilities offer:

### Models with vision

They charge for NxN pixel frames in the analyzed images, and prices vary even according to the model from the same provider.

### Reasoning models

In addition to INPUT tokens (user prompt) and model response tokens (OUTPUT), they also bill for tokens generated during the chain of thought.

### Web search models

They charge for:

1. Prompt tokens (INPUT)
2. Price per thousand searches
3. Search results reading tokens (as INPUT)
4. Final response tokens (OUTPUT)

Although prices remain affordable, I recommend monitoring consumption, especially with search and reasoning functions.

## Next development: connection with self-hosted models

Several users have shown interest in connecting with solutions like Ollama or LLM Studio to run their own models. I plan to work on a “generic connector” compatible with the OpenAI standard during the next month.

Would you be interested in this functionality? Your comments will help me prioritize this development.

I appreciate any suggestions or feedback on this update