diff --git a/.changeset/all-things-cough.md b/.changeset/all-things-cough.md new file mode 100644 index 00000000000..269427d0ab5 --- /dev/null +++ b/.changeset/all-things-cough.md @@ -0,0 +1,5 @@ +--- +"kilo-code": patch +--- + +Add GLM-4.6V model support for z.ai provider diff --git a/packages/types/src/providers/zai.ts b/packages/types/src/providers/zai.ts index e21fcc698bf..9720d663390 100644 --- a/packages/types/src/providers/zai.ts +++ b/packages/types/src/providers/zai.ts @@ -100,6 +100,34 @@ export const internationalZAiModels = { 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.", }, + // kilocode_change start + "glm-4.6v": { + maxTokens: 98_304, + contextWindow: 131_072, + supportsImages: true, + supportsPromptCache: true, + supportsNativeTools: true, + inputPrice: 0.3, + outputPrice: 0.9, + cacheWritesPrice: 0, + cacheReadsPrice: 0.05, + description: + "GLM-4.6V is Z.AI's multimodal visual reasoning model (image/video/text/file input), optimized for GUI tasks, grounding, document/video understanding, native function calling capabilities.", + }, + "glm-4.6v-flash": { + maxTokens: 98_304, + contextWindow: 131_072, + supportsImages: true, + supportsPromptCache: true, + supportsNativeTools: true, + inputPrice: 0, + outputPrice: 0, + cacheWritesPrice: 0, + cacheReadsPrice: 0, + description: + "GLM-4.6V-Flash is a free, high-speed multimodal model with visual reasoning capabilities, excellent for reasoning, coding, and agentic tasks.", + }, + // kilocode_change end "glm-4-32b-0414-128k": { maxTokens: 98_304, contextWindow: 131_072,