Zhipu AI · Uncensored

GLM 4.7 Flash Heretic

GLM 4.7 Flash Heretic — uncensored experimental GLM-4.7-Flash variant optimized for creative freedom and fast inference.

glm-4.7-flash-heretic

Pricing

~50%

Input: $0.034895 / 1,000,000 tokens
Output: $0.1994 / 1,000,000 tokens
Cache read: $0.017448 / 1,000,000 tokens
Cache write: $0.034895 / 1,000,000 tokens

How pricing works

Discount history

50.2%Nov 8, 03:58 AM UTC

Nov 7, 11:59 PMNov 8, 03:58 AM UTC

Model details

Input: text
Output: text
Context window: 200,000 tokens
Maximum output: 32,768 tokens
Availability: $210Uncapped capacity
Updated: 11/8/2026, 4:00:11 AM UTC

Capacity is reserved when your request is accepted.

Capabilities

ChatStreamingTool callingReasoning

Supported parameters

max_tokenstemperaturetop_pfrequency_penaltypresence_penaltyrepetition_penaltymin_plogit_biaslogprobstop_logprobsstoptoolstool_choiceresponse_formatseedstructured_outputsinclude_reasoningreasoning