scriptoriumadmin/Roo-Code
1
0
Fork 0
mirror of https://github.com/RooVetGit/Roo-Code.git synced 2026-10-06 02:47:56 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge a5025ae8cb into c3cae397a1

Browse source
This commit is contained in:
roomote-v0[bot] 2026-04-06 16:32:01 +03:00 • committed by GitHub
commit 58739efcd6
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
2 changed files with 18 additions and 12 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

5
.changeset/glm-5-correct-specs.md Normal file
View file

@ -0,0 +1,5 @@
---
"@roo-code/types": patch
---
Update GLM-5 model specs for Z.ai provider with correct pricing and token limits from official docs (https://docs.z.ai/guides/llm/glm-5)

25
packages/types/src/providers/zai.ts
View file

@ -5,6 +5,7 @@ import { ZaiApiLine } from "../provider-settings.js"
// https://docs.z.ai/guides/llm/glm-4-32b-0414-128k // https://docs.z.ai/guides/llm/glm-4-32b-0414-128k
// https://docs.z.ai/guides/llm/glm-4.5 // https://docs.z.ai/guides/llm/glm-4.5
// https://docs.z.ai/guides/llm/glm-4.6 // https://docs.z.ai/guides/llm/glm-4.6
// https://docs.z.ai/guides/llm/glm-5
// https://docs.z.ai/guides/overview/pricing // https://docs.z.ai/guides/overview/pricing
// https://bigmodel.cn/pricing // https://bigmodel.cn/pricing
@ -121,19 +122,19 @@ export const internationalZAiModels = {
"GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.", "GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.",
}, },
"glm-5": { "glm-5": {
maxTokens: 16_384, maxTokens: 128_000,
contextWindow: 202_752, contextWindow: 200_000,
supportsImages: false, supportsImages: false,
supportsPromptCache: true, supportsPromptCache: true,
supportsReasoningEffort: ["disable", "medium"], supportsReasoningEffort: ["disable", "medium"],
reasoningEffort: "medium", reasoningEffort: "medium",
preserveReasoning: true, preserveReasoning: true,
inputPrice: 0.6, inputPrice: 1.0,
outputPrice: 2.2, outputPrice: 3.2,
cacheWritesPrice: 0, cacheWritesPrice: 0,
cacheReadsPrice: 0.11, cacheReadsPrice: 0.2,
description: 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 is Zhipu's next-generation model with a 200k context window, 128k max output, and built-in thinking capabilities. It delivers state-of-the-art reasoning, coding, and agentic performance.",
}, },
"glm-4.7-flash": { "glm-4.7-flash": {
maxTokens: 16_384, maxTokens: 16_384,
@ -297,19 +298,19 @@ export const mainlandZAiModels = {
"GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.", "GLM-4.7 is Zhipu's latest model with built-in thinking capabilities enabled by default. It provides enhanced reasoning for complex tasks while maintaining fast response times.",
}, },
"glm-5": { "glm-5": {
maxTokens: 16_384, maxTokens: 128_000,
contextWindow: 202_752, contextWindow: 200_000,
supportsImages: false, supportsImages: false,
supportsPromptCache: true, supportsPromptCache: true,
supportsReasoningEffort: ["disable", "medium"], supportsReasoningEffort: ["disable", "medium"],
reasoningEffort: "medium", reasoningEffort: "medium",
preserveReasoning: true, preserveReasoning: true,
inputPrice: 0.29, inputPrice: 0.48,
outputPrice: 1.14, outputPrice: 1.66,
cacheWritesPrice: 0, cacheWritesPrice: 0,
cacheReadsPrice: 0.057, cacheReadsPrice: 0.1,
description: 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 is Zhipu's next-generation model with a 200k context window, 128k max output, and built-in thinking capabilities. It delivers state-of-the-art reasoning, coding, and agentic performance.",
}, },
"glm-4.7-flash": { "glm-4.7-flash": {
maxTokens: 16_384, maxTokens: 16_384,