Skip to content
03 Model garden Serve

GLM 5.3

Instantly via the EU router or as a dedicated GPU deployment. Data stays in Europe.

curl
$ curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-5.3",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Call it now

Drop-in replacement for OpenAI: change only the base URL and API key. The Anthropic format (/v1/messages) is supported too.

Serve Model garden
zai-org/GLM-5.3

text->text · zai-org · sovereign EU

Runs on EU infrastructure operated by European companies, from your request to the GPU. See the full chain

GLM-5.3 uses the same base model as GLM-5.2, every gain comes from post-training.

Router
Router · warm
Dedicated
Dedicated · available
Input (per 1M tokens)
€1.61
Output (per 1M tokens)
€5.06
753BParameters
1,049KContext window
907GBMinimum VRAM
POST /api/v1/chat/completions 200 OK

Specifications

Parameters753B
Context window1,048,576 tokens
Context on every source524,288 tokens · The router sends longer requests to a source where they fit.
Minimum VRAM907 GB
ArchitectureGlmMoeDsaForCausalLM (vLLM)
Licenseother
Modalitytext->text
ReleasedAugust 2026
Publisherzai-org ↗

Pricing

Shared router · per token

€1.61Input (per 1M tokens)
€5.06Output (per 1M tokens)

€0.30 per million cached input tokens

Dedicated GPU · per hour

from €63,12 per hourYour own vLLM instance on European cloud (907 GB VRAM), billed per minute.

Shared EU router, you pay only per token. Dedicated GPU deployments are billed per minute, see pricing.

Bench index

Bench is our quality index for every model, 0 to 100. It rests on public measurements (Epoch AI with about 40 benchmarks, LiveBench, LMArena and more) and is refreshed every morning. Where nobody measures, it shows an estimate with a range.

83.9 / 100 · Measured

Measured by Epoch AI across 16 benchmarks, with a range.

Range 81.3 to 86.8 · Rank 34 of 258 at Epoch AI

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 22-11-2026

LiveBench · 76.1 · Rank 33 of 70

Reasoning85.8
Coding79.0
Agentic coding60.9
Mathematics87.9
Data analysis70.2
Language79.9
Instruction following69.3
Every benchmark (16)
GPQA diamond91.5
OTIS Mock AIME 2024-202591.1
DTBench79.5
WeirdML75.4
FrontierMath-Tiers-1-3-v2-Private72.4
LMCA65.3
SimpleBench59.4
APEX-Agents56.6
ProofBench49.0
SimpleQA Verified41.0
FrontierCode40.1
PostTrainBench34.5
Chess Puzzles33.7
FrontierSWE30.2
FrontierMath-Tier-4-v2-Private29.3
Mystery Game Puzzles26.2
LiveBench · All tasks
Reasoning
theory of mind88.5
zebra puzzle88.8
spatial96.0
logic with navigation70.0
Coding
code generation77.5
code completion80.4
Agentic coding
javascript72.7
typescript50.0
python60.0
Mathematics
AMPS Hard99.0
integrals with game69.0
math comp96.1
olympiad87.5
Data analysis
consecutive events72.3
tablejoin42.4
tablereformat96.1
Language
connections95.3
plot unscrambling60.2
typos84.0
Instruction following
paraphrase64.7
simplify65.9
story generation72.1
summarize74.6
Questions

Frequently asked questions

Can I run GLM 5.3 in the EU?

Yes. HostYourAI runs GLM 5.3 on GPUs in European datacenters via vLLM. Prompts and outputs never leave the EU and there is no US cloud provider in the chain.

Is hosting GLM 5.3 GDPR-compliant?

Yes. All processing happens inside the EU, a Data Processing Agreement (DPA) is available and the subprocessor list is public. Open-source weights also mean: no training on your data.

How much does GLM 5.3 cost?

Via the shared EU router you pay €1.61 per million input tokens and €5.06 per million output tokens, with no fixed costs. For high volume or isolation you can also run GLM 5.3 on a dedicated GPU instance, billed per minute.

Is the API OpenAI-compatible?

Yes. You use the standard OpenAI SDKs with a custom base URL (https://hostyourai.com/api/v1). The Anthropic Messages API is supported as a drop-in as well.

More models from Z.AI

The platform

One platform, four layers

Start with one layer and add the others when the work asks for it. They share one key, one balance and one Activity view.

Code

Your coding agent on open models in Europe, set up with one command.

Open

Control

Keys, budgets and guardrails per team, and personal data stopped before any model sees it.

Open

Serve

Shared per token, or running for you alone, from European data centres.

Open

EU compute

Private GPUs in Europe, H100 to B300, sized for response time, generation speed and concurrent users.

Open

Try GLM 5.3 for free

Creating an account takes a minute. Test GLM 5.3 straight away in the playground.

  • Jantine
  • Hans
  • Sander
  • Jos
  • Daan
  • Kyra
  • Margriet
  • Stan
The team behind HostYourAI