Skip to content

feat: Update Vertex AI Claude Sonnet models to 1M context window #8685

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
roomote wants to merge 13 commits into from
Closed

feat: Update Vertex AI Claude Sonnet models to 1M context window #8685

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
13 commits
Select commit Hold shift + click to select a range
eefe194
feat: enable 1M context window for Claude Sonnet 4 and 4.5 on Vertex AI
roomote Oct 16, 2025
a709b5d
feat(vertex): add [1m] variants for Claude Sonnet models and send ant…
roomote Oct 28, 2025
9d881fe
fix(types): remove supportsComputerUse from Vertex [1m] variants to s…
roomote Oct 28, 2025
d388654
feat(vertex): region-aware pricing for Vertex Claude Sonnet 4/4.5 wit…
roomote Oct 28, 2025
5ddd930
feat(vertex): set [1m] Sonnet pricing to >200k tier and constrain VER…
roomote Oct 28, 2025
b8d52a6
test(webview): restore full VERTEX_REGIONS to satisfy unit tests
roomote Oct 28, 2025
7ed34a1
fix(vertex-pricing): default to under-200k; [1m] variants map to >200…
roomote Oct 28, 2025
3bec87b
fix(vertex): default to under-200k pricing; gate 1M beta header by [1…
roomote Oct 28, 2025
e32d1bf
chore(vertex): remove supportsComputerUse from [1m] variants to align…
roomote Oct 28, 2025
c6d8aaf
feat: generalize "over 200k" large input tier across providers and ap…
roomote Oct 29, 2025
dbd835d
fix(webview-ui): narrow gemini tier typing and pricing fields; re-tri…
roomote Oct 29, 2025
3329fca
fix(cost): make pricing tier selection per-request and avoid auto-sel…
roomote Oct 29, 2025
549ed0b
refactor(vertex): centralize Vertex pricing and 1M context in types h…
roomote Oct 29, 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
4 changes: 2 additions & 2 deletions packages/types/src/providers/vertex.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -165,7 +165,7 @@ export const vertexModels = {
},
"claude-sonnet-4@20250514": {
maxTokens: 8192,
contextWindow: 200_000,
contextWindow: 1_000_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
Expand All @@ -177,7 +177,7 @@ export const vertexModels = {
},
"claude-sonnet-4-5@20250929": {
maxTokens: 8192,
contextWindow: 200_000,
contextWindow: 1_000_000,
supportsImages: true,
supportsComputerUse: true,
supportsPromptCache: true,
Expand Down
28 changes: 28 additions & 0 deletions src/api/providers/__tests__/anthropic-vertex.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -691,6 +691,34 @@ describe("VertexHandler", () => {
expect(modelInfo.info.contextWindow).toBe(200_000)
})

it("should return 1M context window for Claude Sonnet 4", () => {
handler = new AnthropicVertexHandler({
apiModelId: "claude-sonnet-4@20250514",
vertexProjectId: "test-project",
vertexRegion: "us-central1",
})

const modelInfo = handler.getModel()
expect(modelInfo.id).toBe("claude-sonnet-4@20250514")
expect(modelInfo.info).toBeDefined()
expect(modelInfo.info.maxTokens).toBe(8192)
expect(modelInfo.info.contextWindow).toBe(1_000_000)
})

it("should return 1M context window for Claude Sonnet 4.5", () => {
handler = new AnthropicVertexHandler({
apiModelId: "claude-sonnet-4-5@20250929",
vertexProjectId: "test-project",
vertexRegion: "us-central1",
})

const modelInfo = handler.getModel()
expect(modelInfo.id).toBe("claude-sonnet-4-5@20250929")
expect(modelInfo.info).toBeDefined()
expect(modelInfo.info.maxTokens).toBe(8192)
expect(modelInfo.info.contextWindow).toBe(1_000_000)
})

it("honors custom maxTokens for thinking models", () => {
const handler = new AnthropicVertexHandler({
apiKey: "test-api-key",
Expand Down