glm-5-3-flash-260828

Provided by Zhipu · Text model

Parameters

Context window1.0M tokens
Max output131K tokens
Input modalitiestext, image, video, file
Output modalitiestext

Capabilities

Tool callingVision inputReasoningPrompt cachingStructured output

Official pricing

Input$0.1195/M
Output$0.4182/M
Cache read$0.0344/M

Call example

curl -X POST "https://ark.cn-beijing.volces.com/api/v3/chat/completions" -H "Authorization: Bearer $ARK_API_KEY" -H "Content-Type: application/json" -d '{"model":"glm-5-3-flash-260828","messages":[{"role":"user","content":"你好"}],"thinking":{"type":"enabled"},"reasoning_effort":"max","max_tokens":65536,"temperature":1}'