Skip to content

Update mistral-medium prices and context sizes #10729

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom
Open
wants to merge 9 commits into
base: main
Choose a base branch
from
Open

Update mistral-medium prices and context sizes #10729

wants to merge 9 commits into from

Conversation

regismesquita
Copy link
Contributor

While testing the Mistral model, I noticed a discrepancy in the pricing shown on the logs screen. After reviewing the code, I confirmed that the pricing values were incorrect.

This PR corrects the input and output token pricing for the latest Mistral model and adds the newly released mistral-medium-2505 version.

Title

Relevant issues

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

  • I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
  • I have added a screenshot of my new test passing locally
  • My PR passes all unit tests on make test-unit
  • My PR's scope is as isolated as possible, it only solves 1 specific problem

Type

🆕 New Feature
🐛 Bug Fix
🧹 Refactoring
📖 Documentation
🚄 Infrastructure
✅ Test

Changes

@regismesquita
Update mistral-medium prices and context sizes
15a7a4b 
While testing the Mistral model, I noticed a discrepancy in the pricing shown on the logs screen. After reviewing the code, I confirmed that the pricing values were incorrect.

This PR corrects the input and output token pricing for the latest Mistral model and adds the newly released mistral-medium-2505 version.
@vercel Vercel
Copy link

vercel bot commented May 10, 2025 •
edited
Loading

The latest updates on your projects. Learn more about Vercel for Git ↗︎

Name Status Preview Comments Updated (UTC)
litellm ✅ Ready (Inspect) Visit Preview 💬 Add feedback May 20, 2025 8:57am

@CLAassistant
Copy link

CLAassistant commented May 10, 2025 •
edited
Loading

CLA assistant check
All committers have signed the CLA.

@regismesquita regismesquita marked this pull request as ready for review May 10, 2025 22:16
emerzon
emerzon reviewed May 13, 2025
View reviewed changes
Copy link
Contributor

@emerzon emerzon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

The context sizes are incorrect - The previous values were correct.

@regismesquita
Copy link
Contributor Author

regismesquita commented May 14, 2025 •
edited
Loading

@emerzon Mistral medium latest is only 32k?! Every place that I checked shows 128k.

@regismesquita
Copy link
Contributor Author

Does mistral/mistral-medium points to the old one?

@emerzon
Copy link
Contributor

emerzon commented May 14, 2025

@regismesquita It's probably better to add a new entry for the new model matching the API naming from mistral: mistral-medium-2505 and mistral-medium-latest to avoid removing information from the past model.
https://docs.mistral.ai/getting-started/models/models_overview/

Also, mind that the the output context size (max_tokens and max_output_tokens) is not 128k - No clear source but probably still 8k.

@regismesquita
Copy link
Contributor Author

regismesquita commented May 14, 2025 via email •
edited
Loading

@regismesquita
Update model_prices_and_context_window_backup.json
5d31286 
sets mistral medium alias to the old values as it probably points to the old version.
@regismesquita
Update model_prices_and_context_window.json
783cba2
@regismesquita
Copy link
Contributor Author

regismesquita commented May 14, 2025 •
edited
Loading

@emerzon I have reverted mistral/mistral-medium to the old values, and now only the -latest alias and the -2503 aliases are updated/created, I am keeping the 128k value for now while I figure this out, I have asked around and I am trying to confirm the actual values, if I can't find any I will do exploratory requests later today.

@emerzon
Copy link
Contributor

emerzon commented May 14, 2025

128k is for input tokens - not output tokens.

@regismesquita
Copy link
Contributor Author

@emerzon can you share how are you sure of that? I couldn't confirm that anywhere in their docs.

@regismesquita
Copy link
Contributor Author

@emerzon haven't got any response yet, and I do think that it is less than 128k but since I haven't got any response from them I prefer to err on the safe side. so I changed it down to 8191 , and I can follow up later if I found any evidence against it.

@regismesquita regismesquita mentioned this pull request May 15, 2025
Open
@regismesquita regismesquita requested a review from emerzon May 15, 2025 21:27
emerzon
emerzon approved these changes May 17, 2025
View reviewed changes
Copy link
Contributor

@emerzon emerzon left a comment

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

LGTM

@regismesquita OpenHands AI
Copy link
Contributor Author

regismesquita commented May 17, 2025 •
edited
Loading

Ignore this comment.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Reviewers

@emerzon emerzon emerzon approved these changes

Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

Successfully merging this pull request may close these issues.
3 participants
@regismesquita @CLAassistant @emerzon