Skip to content

feat: add GLM-4.6 model support for z.ai provider #8408

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 1 commit into from
Sep 30, 2025
Merged

feat: add GLM-4.6 model support for z.ai provider #8408

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
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
50 changes: 50 additions & 0 deletions packages/types/src/providers/zai.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -32,6 +32,18 @@ export const internationalZAiModels = {
description:
"GLM-4.5-Air is the lightweight version of GLM-4.5. It balances performance and cost-effectiveness, and can flexibly switch to hybrid thinking models.",
},
"glm-4.6": {
maxTokens: 98_304,
Copy link
Author

@roomote roomote bot Sep 30, 2025

Choose a reason for hiding this comment

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

[P3] Please confirm maxTokens for GLM-4.6. With a 204,800 context window, 98,304 mirrors the 4.5 configuration, but it may differ for 4.6 per provider docs.

contextWindow: 204_800,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.6,
outputPrice: 2.2,
cacheWritesPrice: 0,
cacheReadsPrice: 0.11,
description:
"GLM-4.6 is Zhipu's newest model with an extended context window of up to 200k tokens, providing enhanced capabilities for processing longer documents and conversations.",
Copy link
Author

@roomote roomote bot Sep 30, 2025

Choose a reason for hiding this comment

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

[P3] Optional: add a link to the GLM-4.6 docs/announcement in this description for maintainers to verify context window and pricing quickly.

},
} as const satisfies Record<string, ModelInfo>

export type MainlandZAiModelId = keyof typeof mainlandZAiModels
Expand Down Expand Up @@ -101,6 +113,44 @@ export const mainlandZAiModels = {
},
],
},
"glm-4.6": {
maxTokens: 98_304,
contextWindow: 204_800,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.29,
outputPrice: 1.14,
cacheWritesPrice: 0,
cacheReadsPrice: 0.057,
description:
"GLM-4.6 is Zhipu's newest model with an extended context window of up to 200k tokens, providing enhanced capabilities for processing longer documents and conversations.",
tiers: [
{
contextWindow: 32_000,
inputPrice: 0.21,
outputPrice: 1.0,
cacheReadsPrice: 0.043,
},
{
contextWindow: 128_000,
inputPrice: 0.29,
outputPrice: 1.14,
cacheReadsPrice: 0.057,
},
{
contextWindow: 200_000,
Copy link
Author

@roomote roomote bot Sep 30, 2025

Choose a reason for hiding this comment

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

[P2] The 200_000 tier duplicates the Infinity tier pricing. Unless the provider bills differently at exactly 200k, this tier appears redundant and can be removed to reduce noise.

inputPrice: 0.29,
outputPrice: 1.14,
cacheReadsPrice: 0.057,
},
{
contextWindow: Infinity,
inputPrice: 0.29,
outputPrice: 1.14,
cacheReadsPrice: 0.057,
},
],
},
} as const satisfies Record<string, ModelInfo>

export const ZAI_DEFAULT_TEMPERATURE = 0
Expand Down
26 changes: 26 additions & 0 deletions src/api/providers/__tests__/zai.spec.ts
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -71,6 +71,19 @@ describe("ZAiHandler", () => {
expect(model.id).toBe(testModelId)
expect(model.info).toEqual(internationalZAiModels[testModelId])
})

it("should return GLM-4.6 international model with correct configuration", () => {
const testModelId: InternationalZAiModelId = "glm-4.6"
const handlerWithModel = new ZAiHandler({
apiModelId: testModelId,
zaiApiKey: "test-zai-api-key",
zaiApiLine: "international",
})
const model = handlerWithModel.getModel()
expect(model.id).toBe(testModelId)
expect(model.info).toEqual(internationalZAiModels[testModelId])
expect(model.info.contextWindow).toBe(204_800)
Copy link
Author

@roomote roomote bot Sep 30, 2025

Choose a reason for hiding this comment

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

[P3] Consider asserting pricing and supportsPromptCache for GLM-4.6 (both intl and mainland) to catch future config regressions.

})
})

describe("China Z AI", () => {
Expand Down Expand Up @@ -108,6 +121,19 @@ describe("ZAiHandler", () => {
expect(model.id).toBe(testModelId)
expect(model.info).toEqual(mainlandZAiModels[testModelId])
})

it("should return GLM-4.6 China model with correct configuration", () => {
const testModelId: MainlandZAiModelId = "glm-4.6"
const handlerWithModel = new ZAiHandler({
apiModelId: testModelId,
zaiApiKey: "test-zai-api-key",
zaiApiLine: "china",
})
const model = handlerWithModel.getModel()
expect(model.id).toBe(testModelId)
expect(model.info).toEqual(mainlandZAiModels[testModelId])
expect(model.info.contextWindow).toBe(204_800)
})
})

describe("Default behavior", () => {
Expand Down