All models
Head to head
GLM 4.7 Flash Heretic vs GLM 5.3 Flash Uncensored
Price, context, inputs and filters. No benchmarks theatre.
GLM 4.7 Flash Heretic costs 2.5× less per message.
GLM 5.3 Flash Uncensored holds 5.2× more context.
Fact
Made by
Z.AI
Z.AI
Content tier
Uncensored
Uncensored
Intelligence
Quick
Smart & Cheap
Estimated price per message
~0.23 credits≈ 434 messages for 1 €
~0.58 credits≈ 172 messages for 1 €
Context window
200K tokens≈ 308 pages of text in one go
1M tokens≈ 1,613 pages of text in one go
Reads
Text
Text, Images
Writes
Text
Text
Tool use
Yes - search, memory, code and more
Yes - search, memory, code and more
Served via
Venice.ai, Unbottled AI
NanoGPT, Unbottled AI
Status
Legacy
Current
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 €.