GLM 4.7 Flash

Name: GLM 4.7 Flash
Author: Novita AI

mit

GLM-4.7-Flash, a state-of-the-art model in the 30B class, delivers a compelling balance of high performance and efficiency.

Context

200K

Max output

128K

Input price

$0.07/1M tokens

Output price

$0.4/1M tokens

Capabilities

Show unsupported (1)

Reasoning & Interaction

Reasoning

Tool Calling

Output Control

Structured Output

JSON Mode

Infrastructure

Streaming

Prompt Caching

Fine-tuning

Details

Model IDzai-org/glm-4.7-flash

ProviderNovita AI

CreatorZ.AI (Zhipu)

Familyglm-4.7

Licensemit

Statusactive

Typechat

Input modalitiestext

Output modalitiestext

Open weightYes

Parameters—

Architecture—

Context window200K tokens

Max input—

Max output128K tokens

Reasoning tokens—

Knowledge cutoff—

Release date2026-01-19

Sourceofficial

Tools

Function Callingfunction_calling

Call external functions and APIs

Endpoints

Chat CompletionsPOST

Generate chat responses with messageshttps://api.novita.ai/v3/openai/v1/chat/completions

Pricing

Input

$0.07

Output

$0.4

Cache write

—

Cache read

—

Batch in

—

Batch out

—

Family Comparison: glm-4.7

Model	Caps	Perf	Speed	Context	Max out	Pricing
GLM 4.7 Flash	RTJJMSPCF	—	—	200K	128K	$0.07$0.4
GLM 4.7	RTJJMS	—	—	205K	131K	$0.6$2.2
GLM 4.7	RTJJMSPCF	—	—	205K	131K	$0.6$2.2

API

GET/v1/models/novita/zai-org/glm-4.7-flash

GLM 4.7 Flash

zai-org/glm-4.7-flash

GLM-4.7-Flash, a state-of-the-art model in the 30B class, delivers a compelling balance of high performance and efficiency.

Changes · 3 entries

zai-org/glm-4.7-flashcreateca7a400Nov 2, 2026, 03:02 AM

zai-org/glm-4.7-flashupdate639b255Sep 1, 2026, 11:11 AM

nameGLM-4.7-Flash→GLM 4.7 Flash

zai-org/glm-4.7-flashcreate08f0ffeMay 11, 2026, 08:27 AM