Hormouz AIHormouzSign in

Z.ai: GLM 4.5: AI model

GLM-4.5 is a flagship Mixture-of-Experts model with a 128K-token context window, built for agentic workflows and coding. Reachable from inside Iran through Hormouz.

Context window:
131,072 tokens
Input:
$0.6/1M tokens
Output:
$2.2/1M tokens
Type:
text
  • Tools
  • Streaming
  • Long context

Thinking levels:

GLM-4.5 is a flagship language model purpose-built for agent-based applications. It uses a Mixture-of-Experts (MoE) architecture and supports a context window of up to 128K tokens, which makes it well-suited to long documents, large codebases and multi-turn conversations.

The model supports tool calling and structured output, so it is a strong fit for building autonomous assistants, data pipelines and coding tools. GLM-4.5 is served through Hormouz behind an OpenAI-compatible API. Point your base URL at Hormouz, drop in a Hormouz key, and existing OpenAI SDK code runs unchanged.

Pricing is usage-based: $0.60 per million input tokens and $2.20 per million output tokens. Hormouz provides stable access to the model from inside Iran, with no foreign credit card or circumvention tooling required.

GLM-4.5 is our latest flagship foundation model, purpose-built for agent-based applications. It leverages a Mixture-of-Experts (MoE) architecture and supports a context length of up to 128k tokens. GLM-4.5 delivers significantly...

Quickstart

curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'

Specs

VendorZ.ai
TypeText
Context window131,072 tokens
Pricing$0.60/M in · $2.20/M out
APIChat Completions
CapabilitiesStreaming · Tools

Benchmarks

Reasoning

GPQA Diamond
Graduate-level scientific reasoning
78.2%
HLE
Humanity's Last Exam
13%
IFBench
Instruction-following
44.1%
AA-LCR
Long-context reasoning
52.7%
CritPt
Research-level physics reasoning
0%
AA Omniscience
Broad factual knowledge accuracy
25.1%
Non-Hallucination
Rate of avoiding fabricated answers
29.9%

Coding

Terminal-Bench Hard
Agentic coding & terminal use
22%

Agentic

τ²-Bench
Tool-use agents in dual-control scenarios
43%

Source: Artificial Analysis

Design Arena

How Design Arena works ↗
3D
Top 40%
1,181Elo
Win rate: 59.7%Avg time: 109s
Code
Top 55%
1,171Elo
Win rate: 54.4%Avg time: 141s
Data Viz
Top 59%
1,167Elo
Win rate: 53.3%Avg time: 117s
Game Dev
Top 54%
1,158Elo
Win rate: 54.4%Avg time: 140s
SVG
Top 69%
1,095Elo
Win rate: 50.8%Avg time: 36.6s
UI Component
Top 61%
1,151Elo
Win rate: 55%Avg time: 102s
Website
Top 54%
1,176Elo
Win rate: 53.7%Avg time: 148s

Metrics sourced from Design Arena

Code example

cURL
curl https://api.hormouz.net/v1/chat/completions \
  -H "Authorization: Bearer ng-YOUR_API_KEY" \
  -H "Content-Type: application/json" \
  -d '{
    "model": "z-ai/glm-4.5",
    "messages": [{"role": "user", "content": "Hello!"}]
  }'
Python
from openai import OpenAI
client = OpenAI(api_key="ng-YOUR_API_KEY", base_url="https://api.hormouz.net/v1")
response = client.chat.completions.create(
    model="z-ai/glm-4.5",
    messages=[{"role": "user", "content": "Hello!"}],
)
print(response.choices[0].message.content)
JavaScript
import OpenAI from "openai";
const client = new OpenAI({ apiKey: "ng-YOUR_API_KEY", baseURL: "https://api.hormouz.net/v1" });
const response = await client.chat.completions.create({
  model: "z-ai/glm-4.5",
  messages: [{ role: "user", content: "Hello!" }],
});
console.log(response.choices[0].message.content);

Buy the Z.ai: GLM 4.5 API, paid in rial

  • Buy credit with an Iranian bank card; no foreign card or account needed.
  • One Hormouz key reaches Z.ai: GLM 4.5 and 600+ other models, and you pay only for what you use.
  • No VPN and no risk of a banned account; just change the base URL to api.hormouz.net/v1.
Create an account

Use via Hormouz

Connect to this model and 600+ others with one API key, then see usage down to each request.

Request company access

FAQ

How much does GLM-4.5 cost?
Billing is usage-based: $0.60 per million input tokens and $2.20 per million output tokens. There is no fixed monthly fee. You pay only for what you use.
How do I access GLM-4.5 from inside Iran?
Create an account on Hormouz and generate an API key. Hormouz provides a stable path to the model from inside Iran, with no foreign credit card or circumvention tooling required.
Is GLM-4.5 compatible with OpenAI code?
Yes. Hormouz exposes an OpenAI-compatible API. Just change the base URL to Hormouz and swap in your Hormouz key. Your existing SDKs and code run without a rewrite.
What context window and capabilities does GLM-4.5 have?
The model supports a context window of up to 128K tokens and offers tool calling and structured output. These make it a good fit for long documents, codebases and agentic workflows.
What is GLM-4.5 good for?
It is purpose-built for agent-based applications and coding. Building autonomous assistants, developer tooling, long-document summarization and data-processing pipelines.
How does GLM-4.5 compare to others in its family?
GLM-4.5 is the flagship of the family. GLM-4.5 Air is a lighter, more cost-efficient variant better suited to high-volume workloads, while GLM-4.5V adds image understanding. If you need the highest quality for agentic work, the standard GLM-4.5 is the right pick.

Updated 2026-10-13