HostYourAI
Product
EU RouterDecision models like JevHostYourAI CodeOpenAI-compatible APIAnthropic-compatible APIModel GardenDedicated InstancesPlaygroundFine-tuning (Loes)Earn with your GPU
Solutions
Use cases
HostYourAI CodeLLM InferenceRAG pipelinesChatbotsAI agentsFine-tuning
Industries
GovernmentHealthcareFinanceLegal
Models
Kimi K3DeepSeek V4 ProDeepSeek V4 FlashGLM 5.3Kimi K2.7 CodeQwen3.5 397BLlama 3.3 70BMistralMiniMax M3All models →
Compare
Azure OpenAIAWS BedrockClaude APIChatGPTOpenAICompare costs
Resources
DocumentationSavings checkGuide: migrate to the EU RouterGuide: deploy your own LLM (vLLM)Guide: build RAG on EU GPUsModel catalogNewsSecurityFAQ
Pricing News
NL EN DE FR ES
Login Book Demo Get Started
Model garden Router · on request Dedicated · available

GLM 4.5 Air FP8

Runs as your own dedicated GPU deployment, ready to launch from the wizard. Data stays in Europe.

The GLM-4.5 series models are foundation models designed for intelligent agents. GLM-4.5 has 355 billion total parameters with 32 billion active parameters, while GLM-4.5-Air adopts a more compact design with 106 billion total parameters and 12 billion active parameters. GLM-4.5...

Start for free ← All models
zai-org/GLM-4.5-Air-FP8 vLLM ready
text->text · zai-org · sovereign EU
Runs on EU infrastructure operated by European companies; US marketplace capacity is never part of this chain. Full chain
111B
Parameters
131K
Context window
160GB
Minimum VRAM
POST /api/v1/chat/completions On request

Specifications

Parameters 111B
Context window 131,072 tokens
Minimum VRAM 160 GB
Architecture Glm4MoeForCausalLM (vLLM)
License mit
Modality text->text
Released July 2025
Publisher zai-org ↗

Pricing

Shared router · per token
On request
Not available on the shared router. Pricing on request as a dedicated GPU deployment.
Dedicated GPU · per hour
from €5,07 per hour
Your own vLLM instance on European cloud (160 GB VRAM), billed hourly.

Shared EU router, pay-per-token, scale-to-zero. Dedicated GPU deployments are billed hourly, see pricing.

✓ Verified working on 21-07-2026, responded in 120884 ms on our EU infrastructure.

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.

64.3 / 100 · Via LiveBench

Translated from its LiveBench result onto the same scale.

Range 58.0 to 70.7

Sources: Epoch AI ↗ · LiveBench ↗ · LMArena ↗ · Refreshed daily, last on 24-10-2026

LiveBench · 60.5
Reasoning 78.3
Coding 60.3
Agentic coding 16.7
Mathematics 79.4
Data analysis 66.0
Language 44.3
Instruction following 78.8
LiveBench · All tasks
Reasoning
web of lies v3 70.7
zebra puzzle 80.3
spatial 84.0
Coding
code generation 66.2
code completion 54.4
Agentic coding
javascript 10.0
typescript 5.0
python 35.0
Mathematics
AMPS Hard 85.0
math comp 92.7
olympiad 60.4
Data analysis
tablejoin 35.9
tablereformat 96.1
Language
connections 47.7
plot unscrambling 33.2
typos 52.0
Instruction following
paraphrase 76.6
simplify 75.7
story generation 82.9
summarize 80.2

Call it now

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

curl https://hostyourai.com/api/v1/chat/completions \
  -H "Authorization: Bearer hyai-..." \
  -H "Content-Type: application/json" \
  -d '{
    "model": "zai-org/GLM-4.5-Air-FP8",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Frequently asked questions

Can I run GLM 4.5 Air FP8 in the EU?

Yes. HostYourAI runs GLM 4.5 Air FP8 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 4.5 Air FP8 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 4.5 Air FP8 cost?

GLM 4.5 Air FP8 is available on request: through the shared EU router after a quick chat, or as your own dedicated GPU deployment billed per hour. Tell us your use case and we will set it up for you.

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

GLM 5.3 Flash

We introduce GLM-5.3-Flash, the first natively multimodal model in the GLM-5 series. With 320B total parameters and just 18B active parameters, it outperforms GLM-5.2 across benchmarks and real-world workloads at one-tenth the price, while approaching Claude Opus 4.8 on coding and agentic benchmarks.

321B 1M context View model →
GLM 5.3

GLM-5.3 uses the same base model as GLM-5.2 — every gain comes from post-training. Compared with GLM-5.2, it is much better at complex coding and long-horizon tasks:

753B 1M context View model →
GLM 5.2

We're introducing GLM-5.2, our latest flagship model for long-horizon tasks. It marks a substantial leap in long-horizon task capability over its predecessor GLM-5.1 and, for the first time, delivers that capability on a solid 1M-token context. GLM-5.2's new capabilities include: - Solid 1M Context: A solid 1M-token context that stably sustains long-horizon work - Advanced Coding with Flexible Effort: Stronger coding capabilities with multiple thinking effort levels to balance performance and latency - Improved Architecture: We propose IndexShare, which reuses the same indexer across every fou

753B 1M context View model →
GLM 5.1

GLM-5.1 is our next-generation flagship model for agentic engineering, with significantly stronger coding capabilities than its predecessor. It achieves state-of-the-art performance on SWE-Bench Pro and leads GLM-5 by a wide margin on NL2Repo (repo generation) and Terminal-Bench 2.0 (real-world terminal tasks).

754B 203K context View model →
GLM 5

We are launching GLM-5, targeting complex systems engineering and long-horizon agentic tasks. Scaling is still one of the most important ways to improve the intelligence efficiency of Artificial General Intelligence (AGI). Compared to GLM-4.5, GLM-5 scales from 355B parameters (32B active) to 744B parameters (40B active), and increases pre-training data from 23T to 28.5T tokens. GLM-5 also integrates DeepSeek Sparse Attention (DSA), largely reducing deployment cost while preserving long-context capacity.

754B 203K context View model →
GLM 4.7 Flash

GLM-4.7-Flash is a 30B-A3B MoE model. As the strongest model in the 30B class, GLM-4.7-Flash offers a new option for lightweight deployment that balances performance and efficiency.

31B 203K context View model →

Try GLM 4.5 Air FP8 for free

Creating an account takes a minute. Test GLM 4.5 Air FP8 straight away in the playground.

Start for free