Z.AI

GLM 4.7 Flash Heretic

An abliterated GLM 4.7 Flash: refusal behavior stripped out, so it answers instead of lecturing. Pennies per message, fast, calls tools, good for unfiltered chat and creative writing. Same training, same worldview as base GLM: it just stops dodging. Weak at deep analysis. GLM 5.3 Flash Uncensored is the newer, smarter uncensored pick for a bit more.

Chat with GLM 4.7 Flash Heretic

UncensoredTwo kinds, both answer everything. Most are mainstream models with the refusal reflex cut out: same training, same worldview, no more dodging. UncensoredLM is the other kind: its own tuning, its own worldview, political takes that run against the mainstream.

Quick

Intelligence

~0.23 credits

Estimated price per message

200K tokens

Context window

Text

Reads

GLM 4.7 Flash Heretic is a legacy model. Its successor, GLM 5.3 Flash Uncensored, is faster or cheaper - and chats that used GLM 4.7 Flash Heretic move to it automatically.

See GLM 5.3 Flash Uncensored

The facts

Made by

Z.AI

Content tier

Intelligence

Quick

Estimated price per message

~0.23 credits≈ 434 messages for 1 €

Context window

200K tokens≈ 308 pages of text in one go

Reads

Text

Writes

Text

Tool use

Yes - search, memory, code and more

Served via

Venice.ai, Unbottled AI

Status

Legacy

A typical message: 16K tokens in, 1.5K out. Short replies cost less. Models served via OpenRouter bill the real provider cost plus our markup, so actual charges vary. 1 credit = 0.01 €.

Compare GLM 4.7 Flash Heretic

Same facts, side by side.

GLM 4.7 Flash Heretic vs GLM 5.3 Flash Uncensored GLM 4.7 Flash Heretic vs UncensoredLM v1.2 GLM 4.7 Flash Heretic vs Artemis 31B

Try GLM 4.7 Flash Heretic now.

No subscription. Free credits to start. The chat opens with GLM 4.7 Flash Heretic selected and a prompt ready - just send.

Chat with GLM 4.7 Flash Heretic