---
title: "GLM-4.7-Flash — LLM-TEST.com"
url: /models/glm-4-7-flash/
canonical_url: https://llm-test.com/models/glm-4-7-flash/
language: en
type: model
summary: "A free-to-call (rate-limited) Flash model aimed at hobbyists, prototyping, and light production. The open MIT weights mean you can also self-host it without limits."
last_updated: "2026-11-05"
---

# GLM-4.7-Flash

_Zhipu AI · Budget · open weights_

A free-to-call (rate-limited) Flash model aimed at hobbyists, prototyping, and light production. The open MIT weights mean you can also self-host it without limits.

## At a glance

- Released: May 20, 2026
- Provider: Zhipu AI
- Context window: 128,000 tokens
- Max output: 16,000 tokens
- Modalities: Text → text
- Knowledge cutoff: December 2025
- API model ID: `glm-4.7-flash`
- License: Open weights (MIT)

## Pricing

Free to call (rate-limited); open weights can be self-hosted at no per-token cost.

## Best use cases

- **Prototyping** — Build and test ideas at no API cost within the rate limits.
- **Learning** — A no-cost entry point for students and new developers.
- **Light chat** — Powers low-volume assistants where free access matters most.

## Strengths

- Free to call (rate-limited)
- Open weights
- Decent everyday quality

## Limitations

- Rate-limited on the free tier
- Modest reasoning ability

## Where to get access

- Consumer app: Z.ai chat (GLM) — https://chat.z.ai
- API: the Z.ai API console — https://z.ai/manage-apikey/apikey-list
- Also available: open weights on Hugging Face (GLM)
- Docs: https://docs.z.ai

Full comparison and live pricing: https://llm-test.com/ · directory: https://llm-test.com/models/