Skip to content
This repository was archived by the owner on May 15, 2026. It is now read-only.

Commit 043b24b

Browse files
committed
feat: add glm-5-turbo model to Z.ai provider
Add glm-5-turbo to both international and mainland Z.ai model lists with 200k context window, 128k max output tokens, and prompt caching. International pricing: $1.2/M input, $0.24/M cached, $4.0/M output Mainland pricing estimated proportionally from glm-5 ratios. Closes #12018
1 parent 137d3f4 commit 043b24b

1 file changed

Lines changed: 24 additions & 0 deletions

File tree

  • packages/types/src/providers

packages/types/src/providers/zai.ts

Lines changed: 24 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -135,6 +135,18 @@ export const internationalZAiModels = {
135135
description:
136136
"GLM-5 is Zhipu's next-generation model with a 202k context window and built-in thinking capabilities. It delivers state-of-the-art reasoning, coding, and agentic performance.",
137137
},
138+
"glm-5-turbo": {
139+
maxTokens: 128_000,
140+
contextWindow: 200_000,
141+
supportsImages: false,
142+
supportsPromptCache: true,
143+
inputPrice: 1.2,
144+
outputPrice: 4.0,
145+
cacheWritesPrice: 0,
146+
cacheReadsPrice: 0.24,
147+
description:
148+
"GLM-5-Turbo is a high-throughput variant of GLM-5 with a 200k context window and 128k max output tokens, optimized for fast, cost-effective reasoning and coding tasks.",
149+
},
138150
"glm-4.7-flash": {
139151
maxTokens: 16_384,
140152
contextWindow: 200_000,
@@ -311,6 +323,18 @@ export const mainlandZAiModels = {
311323
description:
312324
"GLM-5 is Zhipu's next-generation model with a 202k context window and built-in thinking capabilities. It delivers state-of-the-art reasoning, coding, and agentic performance.",
313325
},
326+
"glm-5-turbo": {
327+
maxTokens: 128_000,
328+
contextWindow: 200_000,
329+
supportsImages: false,
330+
supportsPromptCache: true,
331+
inputPrice: 0.58,
332+
outputPrice: 2.07,
333+
cacheWritesPrice: 0,
334+
cacheReadsPrice: 0.124,
335+
description:
336+
"GLM-5-Turbo is a high-throughput variant of GLM-5 with a 200k context window and 128k max output tokens, optimized for fast, cost-effective reasoning and coding tasks.",
337+
},
314338
"glm-4.7-flash": {
315339
maxTokens: 16_384,
316340
contextWindow: 204_800,

0 commit comments

Comments
 (0)