Skip to content
Merged
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 3 additions & 3 deletions packages/types/src/providers/mistral.ts
Original file line number Diff line number Diff line change
Expand Up @@ -7,9 +7,9 @@ export const mistralDefaultModelId: MistralModelId = "codestral-latest"

export const mistralModels = {
"magistral-medium-latest": {
maxTokens: 41_000,
contextWindow: 41_000,
supportsImages: false,
maxTokens: 8192,
Copy link

Choose a reason for hiding this comment

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

The maxTokens value of 8192 appears inconsistent with the 128k context window and contradicts the PR's goal of reflecting Magistral Medium 1.2's expanded capabilities. Similar models (devstral-medium-latest, mistral-medium-latest) set maxTokens equal to contextWindow (131_000). This restrictive limit would prevent users from generating responses that utilize the full context window. Consider setting maxTokens to 128_000 to match contextWindow, or 131_000 to align with the established pattern.

contextWindow: 128_000,
supportsImages: true,
supportsPromptCache: false,
inputPrice: 2.0,
outputPrice: 5.0,
Expand Down