[PR #11231] [Pixtral] Add new model ; add vision #27132

Closed
opened 2026-02-21 20:40:56 -05:00 by yindo · 0 comments
Owner

Original Pull Request: https://github.com/langgenius/dify/pull/11231

State: closed
Merged: Yes


Summary

This PR adds support for new Mistral AI models, specifically adding configuration for Pixtral models (pixtral-large-latest and pixtral-large-2411) to the model runtime. These models support vision and agent-thought features with a large context window of 128K tokens.

https://mistral.ai/fr/news/pixtral-large/

Changes include:

  • Added new models to _position.yaml
  • Created configuration files for pixtral-large-2411 and pixtral-large-latest
  • Models support vision and agent-thought capabilities
  • Configured with standard parameter rules (temperature, top_p, max_tokens, safe_prompt, random_seed)
  • Set pricing at $0.008/1K tokens for input and $0.024/1K tokens for output

Close https://github.com/langgenius/dify/issues/10896

Screenshots

Before: After:
No Pixtral large models available in model selection Pixtral large models available with vision capabilities

image

image

image

image

Checklist

  • This change requires a documentation update, included: Dify Document
  • I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!)
  • I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change.
  • I've updated the documentation accordingly.
  • I ran dev/reformat(backend) and cd web && npx lint-staged(frontend) to appease the lint gods
**Original Pull Request:** https://github.com/langgenius/dify/pull/11231 **State:** closed **Merged:** Yes --- # Summary This PR adds support for new Mistral AI models, specifically adding configuration for Pixtral models (pixtral-large-latest and pixtral-large-2411) to the model runtime. These models support vision and agent-thought features with a large context window of 128K tokens. https://mistral.ai/fr/news/pixtral-large/ Changes include: - Added new models to `_position.yaml` - Created configuration files for pixtral-large-2411 and pixtral-large-latest - Models support vision and agent-thought capabilities - Configured with standard parameter rules (temperature, top_p, max_tokens, safe_prompt, random_seed) - Set pricing at $0.008/1K tokens for input and $0.024/1K tokens for output Close https://github.com/langgenius/dify/issues/10896 # Screenshots <table> <tr> <td>Before: </td> <td>After: </td> </tr> <tr> <td>No Pixtral large models available in model selection</td> <td>Pixtral large models available with vision capabilities</td> </tr> </table> ![image](https://github.com/user-attachments/assets/a3283b70-c46e-4fb2-8c42-9c272c909939) ![image](https://github.com/user-attachments/assets/0bb9f61c-b3aa-4f0f-80d2-1fb55d702c6e) ![image](https://github.com/user-attachments/assets/8963607e-e05c-4661-866e-c61e5e905985) ![image](https://github.com/user-attachments/assets/658c4ec2-f65f-423a-83a4-fcb92db956f0) # Checklist - [ ] This change requires a documentation update, included: [Dify Document](https://github.com/langgenius/dify-docs) - [x] I understand that this PR may be closed in case there was no previous discussion or issues. (This doesn't apply to typos!) - [x] I've added a test for each change that was introduced, and I tried as much as possible to make a single atomic change. - [x] I've updated the documentation accordingly. - [x] I ran `dev/reformat`(backend) and `cd web && npx lint-staged`(frontend) to appease the lint gods
yindo added the pull-request label 2026-02-21 20:40:56 -05:00
yindo closed this issue 2026-02-21 20:40:56 -05:00
Sign in to join this conversation.
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#27132