GLM-4.7-Flash

GLM-4.7-Flash: a glm-flash model from Zhipu AI, ~200K context, knowledge cutoff 2025-04

Published

scheduleReleased：January 19, 2026

GLM-4.7-Flash is a glm-flash model from Zhipu AI (~200K context, input around $0/1M tokens). Suitable for assistants, content generation, knowledge Q&A and business automation

starsCapabilities

codeFunction calling

paymentsContext and pricing

Context limit200,000

Max output131,072

Knowledge cutoff2025-04

Input price$0/ 1M tokens

Output price$0/ 1M tokens

Cached input price$0/ 1M tokens

descriptionOverview

Overview

GLM-4.7-Flash is provided by Zhipu AI, model ID glm-4.7-flash

Key specs

Context: 200K tokens
Max output: 131.1K tokens
Knowledge cutoff: 2025-04
Input price: $0/1M
Output price: $0/1M

Best for

Consider GLM-4.7-Flash when comparing context length, pricing, multimodal support and relay availability

lightbulbUse cases

Assistants and customer support
Content generation and rewriting
Knowledge Q&A and summarization
Structured extraction

thumb_upStrengths

Very long context (~200K), good for long documents and codebases
Open weights, can be self-hosted
High single-response output limit (~131.1K)

infoLimitations

Knowledge cutoff 2025-04; newer facts need external retrieval
Pricing and availability vary by upstream and relay; verify with official docs and tests

linkReferences

open_in_newhttps://docs.bigmodel.cn/