GLM-5.3

Name: GLM-5.3
Author: Z.ai (Zhipu AI)

Catalogue only Open weights

Sovereignty and hosting

Catalogue only

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Summary

GLM-5.3 is Z.ai’s largest open-weights model at 753B parameters, with a configuration maximum of 1,048,576 tokens and a bespoke "glm-5.3" licence rather than MIT. The vendor states it shares its base model with GLM-5.2 and that all gains come from post-training, and reports 88.8% on Terminal-Bench 2.1 and 64.5% on HLE with tools. The weights are large enough to need a multi-node deployment.

Specifications

Provider: Z.ai (Zhipu AI) (CN)
Context window: 1.0M
Parameters: 753.33B
Modalities: text
License: other · licence
Open weights: yes
Release date: 25 Aug 2026
Tasks: coding, reasoning, summarization, rag

Languages

Strong: en, zh

Adequate: de, fr, es, it, pt, ru, ja, ko

Languages

Strong

Adequate

Not verified: the provider has not documented this claim. — a language is listed as strong only where a source claims it; the card links the evidence where one exists.

When to use it

Strengths

very large context window of 1M tokens
top published agentic and terminal-benchmark scores
open weights, unlike most frontier-scale models

Limits

bespoke Z.ai licence, which must be read before commercial use
753B parameters require a multi-node deployment
all benchmark figures are self-reported by the vendor

Pricing

This model is catalogued for reference. It is not hosted on LLM EU yet, and no first-party endpoint serves it here. Requests to it go to the provider directly, under that provider's own terms.

Verification status

Where a field has no source, the card shows it as unverified instead of filling it in. An empty field is information.

LLM EU Verified means documented, not legally certified. It is not an AI Act conformity assessment and LLM EU is not an EU body.

Versions and variants

catalogue · Catalogue only · weights

Example request

curl https://api.llmeu.com/v1/chat/completions \
  -H "Authorization: Bearer $LLMEU_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{"model":"glm-5-3","messages":[{"role":"user","content":"Hello"}]}'

No playground is deployed for this model: no endpoint serves it, so a request would have nowhere to go.

Benchmarks

Terminal Bench 2.1: 88.8 (vendor-reported) source
Terminal Bench 3.0: 34.6 (vendor-reported) source
HLE with tools: 64.5 (vendor-reported) source
SWE-Marathon v1.1: 42.5 (vendor-reported) source
Published maximum context window (tokens): 1048576 (configuration value) source