Models · Zhipu / Z.ai

GLM-5.3, run in Germany by AKI.IO.

GLM-5.3 is an open-weight model by Zhipu / Z.ai that works with text, released under the GLM-5.3 License. On Evanesca, AKI.IO runs it in Germany, in German data centres according to AKI.IO, and Evanesca keeps no copy of your prompts. If AKI.IO does not answer, Scaleway takes over, in Europe too.

Checked on 20 Oct 2026

GLM-5.3

by Zhipu / Z.ai · GLM-5.3 License

Germany (AKI.IO) Checks 6/6

Input / M: €3.024
Output / M: €9.24
Quick question: €0.0046

Prices per million tokens, VAT included. Quick question: 300 tokens in, 400 out.

The model at a glance

Maker: Zhipu / Z.ai
Licence: GLM-5.3 License
Size: 753B parameters
Context: 512k tokens as the operator announces it
Type: Text
Tool calling: Yes measured by a real call
Reasoning: Yes — it thinks before answering those tokens are billed as output
Run by: AKI.IO AKI.IO GmbH, Berlin — a German company; its shareholders are not published Fallback: Scaleway
Where it runs: Germany (AKI.IO)
Checks: 6/6 All six: Licence, Provenance, Security, GDPR, Benchmarks and Live test
Price: €3.024 per million input tokens · €9.24 per million output tokens VAT included; reasoning tokens count as output
Open weights: Yes published by the maker: an operator can run the model
Model card: huggingface.co/zai-org/GLM-5.3

Where your prompts go

Here is the route of a message sent to GLM-5.3, end to end. No call to the model leaves Europe: not as a backup, not when servers are busy.

From your browser to EvanescaEvanesca passes your message straight on to AKI.IO. It stores neither the prompt nor the answer: both stay in memory only while the answer is written.
AKI.IO, GermanyAKI.IO runs GLM-5.3 in Germany: AKI.IO says inference runs on GPU infrastructure in German data centres (AKI.IO, read on 13 Oct 2026). AKI.IO GmbH is a German company in Berlin; its shareholders are not published. As a company under German law, it is out of the CLOUD Act's direct reach. AKI.IO states that “prompts, inputs, and generated outputs are processed in volatile memory and are not logged, stored, or analyzed by AKI.IO” (AKI.IO); its privacy policy keeps usage data — request ID, model, status, timestamps, token usage — for 90 days, for billing and service maintenance (AKI.IO's privacy policy).
Back to you, with its passportThe answer comes back with its passport: model, operator, country, and what was kept. Your history lives in your browser; about this message, Evanesca keeps only billing data — tokens and cost.

What it costs

€3.024 per million input tokens and €9.24 per million output tokens, VAT included. Three typical exchanges on GLM-5.3:

COST OF AN EXCHANGE · VAT INCLUDED
Example	Tokens in	Tokens out	Cost
A quick question	300	400	€0.0046
A long document to summarise	15,000	800	€0.0528
A message late in a long conversation	40,000	2,000	€0.1394

€2 of credit covers about 430 quick questions on this model. Reasoning tokens count as output, so a model that thinks first can cost more than these examples. The exact cost of each answer shows under it. All prices.

Licence

Zhipu / Z.ai publishes GLM-5.3 under the GLM-5.3 License. A licence of its own, to read before any commercial use (licence text).

The official model card is the reference.

Similar models

Same maker first, then the same type.

Paris, France

GLM-5.2

Zhipu / Z.ai · Text · checks 6/6

€3.024 · €9.24 / M tokens

Paris, France

DeepSeek V4 Flash

DeepSeek · Text · checks 6/6

€0.672 · €1.344 / M tokens

Paris, France

GPT-OSS 120B

OpenAI · Text · checks 5/6

€0.252 · €1.008 / M tokens

Paris, France

Qwen3 235B

Qwen · Text · checks 5/6

€1.26 · €3.78 / M tokens

Paris, France

Llama 3.3 70B

Meta · Text · checks 5/6

€1.512 · €1.512 / M tokens

Every model, with its operator and where it runs

Frequently asked questions

Where does GLM-5.3 run on Evanesca?

In Germany, at AKI.IO: AKI.IO says inference runs on GPU infrastructure in German data centres (AKI.IO, read on 13 Oct 2026). AKI.IO GmbH is a German company in Berlin, so your prompts stay out of the CLOUD Act's direct reach. Its shareholders are not published. If AKI.IO does not answer, Scaleway takes over, in France too. No call to the model leaves Europe: not as a backup, not when servers are busy.

Does Evanesca keep what I send to GLM-5.3?

No. The prompt and the answer stay in memory only while the answer is written, and your history lives in your browser; about your messages, Evanesca keeps only billing data — tokens and cost. AKI.IO states that “prompts, inputs, and generated outputs are processed in volatile memory and are not logged, stored, or analyzed by AKI.IO” (AKI.IO); its privacy policy keeps usage data — request ID, model, status, timestamps, token usage — for 90 days, for billing and service maintenance (AKI.IO's privacy policy).

How much does GLM-5.3 cost?

€3.024 per million input tokens and €9.24 per million output tokens, VAT included. A quick question — 300 tokens in, 400 out — costs about €0.0046. There is no subscription: credit starts at €2.

Can GLM-5.3 call tools?

Yes: a real call through AKI.IO returned proper tool calls (function calling).

Which licence is GLM-5.3 under?

GLM-5.3 License. A licence of its own, to read before any commercial use (licence text).

Which checks has GLM-5.3 passed?

6 of 6: Licence, Provenance, Security, GDPR, Benchmarks and Live test. Its passport shows the same stamps; how each check works.

Does Zhipu / Z.ai see what I type?

No. Zhipu / Z.ai published the weights, and AKI.IO runs them in Germany: your prompts go to AKI.IO, not to Zhipu / Z.ai. AKI.IO adds that “model developers do not receive access to customer inference content through AKI.IO” (AKI.IO, read on 13 Oct 2026).