CERBERUS/LibreChat
1
0
Fork 0
mirror of https://github.com/danny-avila/LibreChat.git synced 2026-10-22 01:53:33 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 6

🪙 feat: Add Token Pricing for Devstral, Voxtral, Holo2, and Mistral Medium (#13863)

Browse source 
These open-weight models are not in tokenValues, so they fall back to
defaultRate ($6/1M) for balance/transaction accounting on custom
OpenAI-compatible endpoints (e.g. Scaleway, where they are served).
Add representative per-1M-token USD rates:

- devstral        0.4 / 2.0   (Mistral API pricing)
- mistral-medium  1.5 / 7.5   (Mistral API pricing, Medium 3.5)
- voxtral(-small) 0.1 / 0.4   (Mistral API pricing, text)
- holo2           0.3 / 0.7   (Scaleway Generative APIs public pricing)

Generic keys are used so versioned ids (e.g. devstral-2-123b-instruct-2512,
mistral-medium-3.5-128b, voxtral-small-24b-2507, holo2-30b-a3b) match via the
existing longest-substring lookup.
This commit is contained in:
Pascal Garber 2026-06-20 17:34:09 +02:00 • committed by GitHub
parent 229c54c843
commit dfc1178031
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
1 changed files with 5 additions and 0 deletions
Download patch file Download diff file Expand all files Collapse all files

5
packages/data-schemas/src/methods/tx.ts
View file

@ -217,6 +217,11 @@ export const tokenValues: Record<string, { prompt: number; completion: number }>
'grok-4-1-fast': { prompt: 0.2, completion: 0.5 },
'grok-code-fast': { prompt: 0.2, completion: 1.5 },
codestral: { prompt: 0.3, completion: 0.9 },
devstral: { prompt: 0.4, completion: 2.0 },
'mistral-medium': { prompt: 1.5, completion: 7.5 },
voxtral: { prompt: 0.1, completion: 0.4 },
'voxtral-small': { prompt: 0.1, completion: 0.4 },
holo2: { prompt: 0.3, completion: 0.7 },
'ministral-3b': { prompt: 0.04, completion: 0.04 },
'ministral-8b': { prompt: 0.1, completion: 0.1 },
'mistral-nemo': { prompt: 0.15, completion: 0.15 },