Skip to content

feat: add claude 4 models to vertex ai specs #3843

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

Closed
wants to merge 2 commits into from
Closed

feat: add claude 4 models to vertex ai specs #3843

Changes from 1 commit
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b66dc19
feat: add claude 4 models to vertex ai specs
plucked May 22, 2025
77133a8
chore: reduced maxTokens to 8192 in the non-thinking variants
plucked May 22, 2025
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
48 changes: 48 additions & 0 deletions src/shared/api.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -582,6 +582,54 @@ export const vertexModels = {
inputPrice: 1.25,
outputPrice: 5,
},
"claude-sonnet-4@20250514:thinking": {
maxTokens: 64_000,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
thinking: true,
},
"claude-sonnet-4@20250514": {
maxTokens: 64_000,
Copy link
Collaborator

@mrubens mrubens May 22, 2025

Choose a reason for hiding this comment

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

Same question here - maybe we should make this 8192 like 3.7

Copy link
Author

@plucked plucked May 22, 2025

Choose a reason for hiding this comment

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

will do

Copy link
Author

@plucked plucked May 22, 2025

Choose a reason for hiding this comment

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

I updated it to 8192, you were right, that value is more reasonable

contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 3.0,
outputPrice: 15.0,
cacheWritesPrice: 3.75,
cacheReadsPrice: 0.3,
thinking: false,
},
"claude-opus-4@20250514:thinking": {
maxTokens: 32_000,
contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 15.0,
outputPrice: 75.0,
cacheWritesPrice: 18.75,
cacheReadsPrice: 1.5,
thinking: true,
},
"claude-opus-4@20250514": {
maxTokens: 32_000,
Copy link
Collaborator

@mrubens mrubens May 22, 2025

Choose a reason for hiding this comment

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

Do we still want this many max tokens for the non-thinking version?

Copy link
Author

@plucked plucked May 22, 2025

Choose a reason for hiding this comment

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

Updated it here as well

contextWindow: 200_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
inputPrice: 15.0,
outputPrice: 75.0,
cacheWritesPrice: 18.75,
cacheReadsPrice: 1.5,
thinking: false,
},
"claude-3-7-sonnet@20250219:thinking": {
maxTokens: 64_000,
contextWindow: 200_000,
Expand Down