Skip to content

Feature/update vertex ai models and regions #7727

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

Merged
merged 2 commits into from
Sep 7, 2025
Merged

Feature/update vertex ai models and regions #7727

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
b3f1418
feat: update Vertex AI provider list with gpt-oss, qwen3, deepseek, m…
ssweens Sep 6, 2025
3b90450
test: updated vertex provider tests to allow new region
ssweens Sep 6, 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
55 changes: 55 additions & 0 deletions packages/types/src/providers/vertex.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -294,6 +294,60 @@ export const vertexModels = {
outputPrice: 1.15,
description: "Meta Llama 4 Maverick 17B Instruct model, 128K context.",
},
"deepseek-r1-0528-maas": {
maxTokens: 32_768,
contextWindow: 163_840,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.35,
outputPrice: 5.4,
description: "DeepSeek R1 (0528). Available in us-central1",
},
"deepseek-v3.1-maas": {
maxTokens: 32_768,
contextWindow: 163_840,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.6,
outputPrice: 1.7,
description: "DeepSeek V3.1. Available in us-west2",
Copy link

@roomote roomote bot Sep 6, 2025

Choose a reason for hiding this comment

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

I noticed the description mentions "Available in us-west2" while the other DeepSeek model (deepseek-r1-0528-maas) mentions us-central1. Is this intentional? The issue #7725 mentioned these models need us-south1 support, so I wanted to confirm if this model is actually available in us-west2 or if it should be us-south1 instead?

Copy link
Author

@ssweens ssweens Sep 6, 2025 •
edited
Loading

Choose a reason for hiding this comment

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

Good call out. This is intentional. Google Vertex AI models are not always global so you have to know which region is required for each model, and there is no pattern to it. Each requires manually finding the right model page in Google Vertex AI's model garden listings.

These values are provided here for significant convenience and better UX flow. By leveraging the description field, it presents the value in a context-relevant, (IMO) appropriate location without building some new Vertex-only field, and helps the user keep flow and not be required to go hunt down these values and leave their current UX setting. This should be a major convenience. All values provided are manually verified in the Google Vertex documentation, sample here: https://cloud.google.com/vertex-ai/generative-ai/docs/maas/deepseek/deepseek-v31

},
"gpt-oss-120b-maas": {
maxTokens: 32_768,
contextWindow: 131_072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.15,
outputPrice: 0.6,
description: "OpenAI gpt-oss 120B. Available in us-central1",
},
"gpt-oss-20b-maas": {
maxTokens: 32_768,
contextWindow: 131_072,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.075,
outputPrice: 0.3,
description: "OpenAI gpt-oss 20B. Available in us-central1",
},
"qwen3-coder-480b-a35b-instruct-maas": {
maxTokens: 32_768,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 1.0,
outputPrice: 4.0,
description: "Qwen3 Coder 480B A35B Instruct. Available in us-south1",
},
"qwen3-235b-a22b-instruct-2507-maas": {
maxTokens: 16_384,
contextWindow: 262_144,
supportsImages: false,
supportsPromptCache: false,
inputPrice: 0.25,
outputPrice: 1.0,
description: "Qwen3 235B A22B Instruct. Available in us-south1",
},
} as const satisfies Record<string, ModelInfo>

export const VERTEX_REGIONS = [
Expand All @@ -302,6 +356,7 @@ export const VERTEX_REGIONS = [
{ value: "us-east1", label: "us-east1" },
{ value: "us-east4", label: "us-east4" },
{ value: "us-east5", label: "us-east5" },
{ value: "us-south1", label: "us-south1" },
{ value: "us-west1", label: "us-west1" },
{ value: "us-west2", label: "us-west2" },
{ value: "us-west3", label: "us-west3" },
Expand Down
1 change: 1 addition & 0 deletions webview-ui/src/components/settings/providers/__tests__/Vertex.spec.tsx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -74,6 +74,7 @@ describe("Vertex", () => {
{ value: "us-east1", label: "us-east1" },
{ value: "us-east4", label: "us-east4" },
{ value: "us-east5", label: "us-east5" },
{ value: "us-south1", label: "us-south1" },
{ value: "us-west1", label: "us-west1" },
{ value: "us-west2", label: "us-west2" },
{ value: "us-west3", label: "us-west3" },
Expand Down
Loading