scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-09-07 08:26:51 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat: add glm-5-turbo model to Z.ai provider

Browse source 
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
This commit is contained in:
Roo Code 2026-03-27 22:21:31 +00:00
parent 137d3f4fd8
commit 043b24b16d
1 changed files with 24 additions and 0 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
packages/types/src/providers/zai.ts
View file

@ -135,6 +135,18 @@ export const internationalZAiModels = {
description:
"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.",
},
"glm-5-turbo": {
maxTokens: 128_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 1.2,
outputPrice: 4.0,
cacheWritesPrice: 0,
cacheReadsPrice: 0.24,
description:
"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.",
},
"glm-4.7-flash": {
maxTokens: 16_384,
contextWindow: 200_000,
@ -311,6 +323,18 @@ export const mainlandZAiModels = {
description:
"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.",
},
"glm-5-turbo": {
maxTokens: 128_000,
contextWindow: 200_000,
supportsImages: false,
supportsPromptCache: true,
inputPrice: 0.58,
outputPrice: 2.07,
cacheWritesPrice: 0,
cacheReadsPrice: 0.124,
description:
"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.",
},
"glm-4.7-flash": {
maxTokens: 16_384,
contextWindow: 204_800,